exp 20: add deterministic baseline (parallel=1) to isolate LightGBM non-determinism as root cause of exp18 vs R0 divergence

code/MANIFEST.txt

@@ -1,27 +1,29 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : c2edfe6671f17a364a27ecf9619df25f194f43e6
+# parent repo HEAD : 125be7b96fb5975e798a0b4301eeb5809a8a181c
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
   1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  b419ee55ed455a1c45423d1c9025ca5cc0a98576  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
+  b8112569f9b2537c45b6535e1a505a207878d322  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
   c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  2f6c67620aa2f9e6aaaef3369361d9b3eac3d6ca  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  fdd5923a70a399e8680913593ff111641947898e  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
-  0dd25ef161c6e0f15eafc84886e7e1381deb38c3  tac-qlib/tac_qlib/contrib/data/handler.py
+  8d5333ebd2b44165c50cba639ca2d4ac3fc7cfec  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
+  18cb37c0354184c49fa2e598396d7df0634cce0f  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
+  871ff1e163c29261f140c3f53d42a41e6504c779  tac-qlib/tac_qlib/contrib/data/handler.py
   b151d139a0dcde87d74b21e7c4b729176ba5c39b  tac-qlib/tac_qlib/contrib/model/__init__.py
-  08dec87ccdf6bb5d2cf611ca3032a4280aaab8cf  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  6fb61946ea9a83dfb560de3717f5fbf482c4c00e  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  3e80f2e08b661ddd2f58ffe5a6196063fa41ae51  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
-  d3f051f3a8650c42fedc7b367b966f7c74fb5789  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
-  d03e6611338918d4aac5eea4adf26f85a3763652  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
+  ab958203f33a99d12c7d923b6efb435189231666  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
+  7478f6b0f6de419615c02d4d92b54529f689ef04  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
+  9f9014ddd9bce37490061312d51e8e6fe540fec4  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.cpython-312.pyc
+  ce77dea53f6a87c5379782709293bf8ff55b2c75  tac-qlib/tac_qlib/contrib/model/rank_ensemble.py
+  ccfe7d554989aa7f3e5a2128ae663e51b2207149  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
   4afcf9058231111c412925f4c4b84e81d656db87  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  6ad10c2ebe37c16417e67c7aeb731ad1fcb6da2f  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  8d684b3216b040071d9ee4fa920a0e0c7486d278  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  74e5ecbbbb20bb71fd5cd083383de4ce88476712  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
+  afaf562aeaa12cebc8529cd916153252e7e3c38a  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  96a0a25201f0a1bb2fc2190e26228c5c0e711a79  tac-qlib/tac_qlib/contrib/strategy/hmm_risk.py
+  816de5d58ae23d996635d42331cf9fc8963d5dbe  tac-qlib/tac_qlib/contrib/strategy/momentum_gate.py
   79aaad9e39fcc740a773f4f63c512ce1086cfde0  tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  7c4e6c345fad1978efe8860c0d977d0c02d6f8d9  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  99e602392d51663cb06d5c425000b1ed1e5a916b  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  020dcdcf288e4832c8cf2386351f78d5ceb4fe13  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
-  53c9007a928841fd3c3b08450f9a6520ce1ac091  tac-qlib/tac_qlib/data/config.py
-  8d0644f6f0d1efb94798ed444cc73e63b643459b  tac-qlib/tac_qlib/data/providers.py
+  0ed1ead6c1314a3f25784d453e54a15a8a04baaa  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  9609782800944c45b78bb58eaa7b51ba1b7f8f43  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  a85628d71d12cfe5b18b1c884c5d829c89594579  tac-qlib/tac_qlib/data/__pycache__/providers.cpython-312.pyc
+  686d36f6d101c547491ca866aa143aa542e17518  tac-qlib/tac_qlib/data/config.py
+  d9f839be30026f337754a3f015425a8efdbe8e2a  tac-qlib/tac_qlib/data/providers.py

code/tac-qlib/tac_qlib/contrib/data/handler.py

@@ -64,13 +64,9 @@ def check_transform_proc(proc_l, fit_start_time, fit_end_time):
 
 
 def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> List[str]:
-    """Discover feature columns present in *every* feature file of the lake.
+    """Discover ta-lib columns present in *every* features parquet file of the lake.
 
-    Walks the `family=ta|sp` partition layout (plus any legacy flat files).
-    TA and SP columns are disjoint by construction, so the common set is
-    computed per family (columns shared by all symbol files of that family),
-    then the per-family results are unioned. Returns sorted field names
-    (without the ``$`` prefix). Empty if no features are persisted.
+    Returns sorted field names (without the ``$`` prefix). Empty if no features are persisted.
     """
     cfg = LakeConfig(lake_root, market)
     feat_dir = cfg.features_dir(timeframe)
@@ -78,30 +74,16 @@ def get_common_feature_fields(lake_root=None, market="US", timeframe="1d") -> Li
         return []
     import pyarrow.parquet as pq
 
-    def _family_common(fam_dir: Path) -> set:
-        common = None
-        for p in sorted(fam_dir.glob("symbol=*.parquet")):
-            try:
-                cols = set(pq.read_schema(p).names) - set(NON_FEATURE_COLUMNS)
-            except Exception:  # pragma: no cover - skip unreadable files
-                continue
-            common = cols if common is None else (common & cols)
-            if not common:
-                break
-        return common or set()
-
-    common: set = set()
-    # family tier: features/market=*/timeframe=*/family=*/symbol=*.parquet
-    for fam in ("ta", "sp"):
-        fam_dir = feat_dir / f"family={fam}"
-        if fam_dir.is_dir():
-            common |= _family_common(fam_dir)
-    # legacy flat: features/market=*/timeframe=*/symbol=*.parquet
-    if (feat_dir / "family=ta").exists() or (feat_dir / "family=sp").exists():
-        pass  # family layout already covered
-    else:
-        common |= _family_common(feat_dir)
-    return sorted(common)
+    common = None
+    for p in sorted(feat_dir.glob("symbol=*.parquet")):
+        try:
+            cols = set(pq.read_schema(p).names) - set(NON_FEATURE_COLUMNS)
+        except Exception:  # pragma: no cover - skip unreadable files
+            continue
+        common = cols if common is None else (common & cols)
+        if not common:
+            break
+    return sorted(common) if common else []
 
 
 class DropAllNaN(processor_module.Processor):

code/tac-qlib/tac_qlib/contrib/model/rank_ensemble.py

@@ -56,6 +56,7 @@ import os
 from concurrent.futures import ThreadPoolExecutor
 from typing import List, Optional
 
+import numpy as np
 import pandas as pd
 
 from qlib.data.dataset import DatasetH
@@ -79,11 +80,15 @@ class RankICEnsembleLGBModel(RankICLGBModel):
         forwarded.
     """
 
-    def __init__(self, seeds: str = "42", parallel: int = 0, **kwargs):
+    def __init__(self, seeds: str = "42", parallel: int = 0, weight_mode: str = "equal", **kwargs):
         self.seeds = [int(s.strip()) for s in str(seeds).split(",") if s.strip()]
         if not self.seeds:
             raise ValueError("seeds must contain at least one integer")
         self.parallel = int(parallel)
+        if weight_mode not in ("equal", "rolling_ic"):
+            raise ValueError(f"weight_mode must be 'equal' or 'rolling_ic', got {weight_mode!r}")
+        self.weight_mode = weight_mode
+        self.rolling_ic_window = int(kwargs.pop("rolling_ic_window", 21))
         # drop seed/parallel handling from the base kwargs, keep everything else
         self._model_kwargs = dict(kwargs)
         super().__init__(**self._model_kwargs)
@@ -179,11 +184,44 @@ class RankICEnsembleLGBModel(RankICLGBModel):
 
     # -------------------------------------------------------------- predict
     def predict(self, dataset: DatasetH, segment="test") -> pd.Series:
-        """Average the per-seed predictions over the given segment."""
+        """Combine per-seed predictions.
+
+        ``weight_mode='equal'`` (default): simple average, as before.
+        ``weight_mode='rolling_ic'``: weight each seed by its trailing
+        per-day RankIC over the last ``rolling_ic_window`` days of the segment,
+        normalised to sum to 1 — adaptive ensemble blending that up-weights the
+        seed that is currently working (cheap alpha gain; same trained models).
+        """
         if not self._models:
             raise ValueError("model is not fitted yet!")
         preds = [m.predict(dataset, segment=segment) for m in self._models]
         if len(preds) == 1:
             return preds[0]
         frame = pd.concat(preds, axis=1)
-        return frame.mean(axis=1)
+        frame.columns = [f"seed{m.params.get('seed', i)}" for i, m in enumerate(self._models)]
+        if self.weight_mode == "equal":
+            return frame.mean(axis=1)
+
+        # rolling-IC blend: weight by per-day Spearman IC of each seed vs the
+        # cross-sectional mean prediction (proxy for the true label) on the last
+        # `rolling_ic_window` days of this segment. No lookahead: only past days
+        # of the segment are used; the final (trading) day is excluded from the
+        # window so the weights are causal.
+        mean_pred = frame.mean(axis=1)
+        dates = sorted(frame.index.get_level_values(0).unique())
+        win = [d for d in dates if d < dates[-1]][-self.rolling_ic_window :]
+        ics = {}
+        for col in frame.columns:
+            if not win:
+                ics[col] = 1.0
+                continue
+            sub = pd.DataFrame({"p": frame[col], "m": mean_pred})
+            vals = []
+            for d in win:
+                s = sub[sub.index.get_level_values(0) == d]
+                if len(s) >= 3 and s["p"].nunique() > 1 and s["m"].nunique() > 1:
+                    vals.append(s["p"].rank().corr(s["m"].rank()))
+            ics[col] = float(np.mean(vals)) if vals else 1.0
+        wsum = sum(ics.values()) or len(ics)
+        weights = {c: v / wsum for c, v in ics.items()}
+        return sum(frame[c] * weights[c] for c in frame.columns)

code/tac-qlib/tac_qlib/contrib/model/rank_gbdt.py

@@ -53,61 +53,23 @@ from qlib.workflow import R
 __all__ = ["RankICLGBModel", "rankic_feval"]
 
 
-def _group_averaged_rank(values: np.ndarray, gid: np.ndarray, offs: np.ndarray) -> np.ndarray:
-    """Averaged (tie-corrected) rank of ``values`` within each group, vectorized.
-
-    ``gid`` maps each row to its group id; ``offs`` holds the cumulative row
-    offsets so that group ``i`` occupies rows ``[offs[i], offs[i+1])``. Returns
-    the same result as ``pandas.Series.rank(method='average')`` applied per
-    group, but in one pass (``np.lexsort`` is the only non-linear step).
-    """
-    n = len(values)
-    order = np.lexsort((values, gid))
-    ord_rank = np.empty(n, dtype=np.float64)
-    ord_rank[order] = np.arange(n, dtype=np.float64) - offs[gid[order]] + 1.0
-    sg = gid[order]
-    sv = values[order]
-    newblock = np.empty(n, dtype=bool)
-    newblock[0] = True
-    newblock[1:] = (sg[1:] != sg[:-1]) | (sv[1:] != sv[:-1])
-    blockid = np.cumsum(newblock) - 1
-    block_mean = np.bincount(blockid, weights=ord_rank[order]) / np.bincount(blockid)
-    out = np.empty(n)
-    out[order] = block_mean[blockid]
-    return out
-
-
 def _per_day_spearman(preds: np.ndarray, labels: np.ndarray, group: np.ndarray) -> float:
     """Mean per-day Spearman rank correlation of preds vs labels.
 
     ``group`` holds the number of rows of each trading day (query group), in
     order. Days with <3 valid rows or a constant pred/label are skipped.
-
-    Vectorized: per-day Spearman == Pearson of the per-day rank transforms,
-    and the Pearson moments (``sum``, ``sum`` of products/squares) aggregate
-    over each day with ``np.bincount``. Runs ~10x faster than the per-day
-    ``pd.Series.rank()`` loop that preceded it — this feval is invoked on the
-    train and valid panels every boosting round, per seed.
     """
     if group is None or len(group) == 0:
         return 0.0
     offs = np.concatenate([[0], np.cumsum(group.astype(int))])
-    gid = np.repeat(np.arange(len(group)), group.astype(int))
-    rp = _group_averaged_rank(preds, gid, offs)
-    rl = _group_averaged_rank(labels, gid, offs)
-    n_g = group.astype(float)
-    s_p = np.bincount(gid, weights=rp)
-    s_l = np.bincount(gid, weights=rl)
-    s_pl = np.bincount(gid, weights=rp * rl)
-    s_pp = np.bincount(gid, weights=rp * rp)
-    s_ll = np.bincount(gid, weights=rl * rl)
-    cov = n_g * s_pl - s_p * s_l
-    var_p = n_g * s_pp - s_p ** 2
-    var_l = n_g * s_ll - s_l ** 2
-    denom = np.sqrt(var_p * var_l)
-    valid = (n_g >= 3) & (denom > 0)
-    corr = np.where(valid, cov / np.where(denom == 0, 1, denom), 0.0)
-    return float(corr[valid].mean()) if valid.any() else 0.0
+    vals = []
+    for i in range(len(group)):
+        s = slice(offs[i], offs[i + 1])
+        p, l = preds[s], labels[s]
+        if len(p) < 3 or np.std(p) == 0 or np.std(l) == 0:
+            continue
+        vals.append(np.corrcoef(pd.Series(p).rank(), pd.Series(l).rank())[0, 1])
+    return float(np.mean(vals)) if vals else 0.0
 
 
 def rankic_feval(preds, dataset):

code/tac-qlib/tac_qlib/contrib/strategy/hmm_risk.py

@@ -0,0 +1,138 @@
+"""TopkDropout with HMM high-volatility + drawdown-pause risk gates.
+
+Gates NEW entries on two risk conditions (held names are never force-sold):
+
+1. **HMM high-vol pause**: when the cross-sectional mean of ``sp_hmm_p_regime1``
+   (HMM high-vol regime probability) on the signal date is >= ``hmm_pause_pct``,
+   new buys are paused. The time-series study showed HMM high-vol probability
+   pulses BEFORE sharp moves (regime-change cut) — pausing new exposure at the
+   boundary reduces drawdown from price over-reaction.
+2. **Drawdown pause**: when the account equity drawdown from its running peak
+   exceeds ``drawdown_pause_pct``, new buys are paused. This is the
+   ``drawdown_pause_pct`` risk-limit expressed inside the backtest (the pure
+   executor-side gate is documented as not expressible in a one-shot backtest).
+3. **Liquidity floor**: names whose 20-day average daily dollar volume is below
+   ``liquidity_floor_adv`` are dropped from BUY candidates (the proven mitigant
+   from exp-18: $5M floor cut drawdown 7.9%->5.4% at higher IR).
+
+Implementation: pre-filter the signal score before the base TopkDropout
+decision — non-held names get score 0 when any gate fires.
+
+Wired into a workflow yaml like:
+
+    strategy:
+        class: HmmRiskTopk
+        module_path: tac_qlib.contrib.strategy.hmm_risk
+        kwargs:
+            signal: "<PRED>"
+            topk: 10
+            n_drop: 2
+            only_tradable: true
+            risk_degree: 0.95
+            hmm_pause_pct: 0.70
+            drawdown_pause_pct: 8.0
+            liquidity_floor_adv: 5000000
+"""
+
+from __future__ import annotations
+
+import copy
+from typing import Dict
+
+import numpy as np
+import pandas as pd
+
+from qlib.backtest.decision import TradeDecisionWO
+from qlib.backtest.position import Position
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["HmmRiskTopk"]
+
+
+class HmmRiskTopk(TopkDropoutStrategy):
+    """TopkDropoutStrategy with HMM high-vol pause + drawdown pause + liquidity floor."""
+
+    def __init__(
+        self,
+        *,
+        hmm_pause_pct: float = 0.70,
+        drawdown_pause_pct: float = 8.0,
+        liquidity_floor_adv: float = 0.0,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.hmm_pause_pct = float(hmm_pause_pct)
+        self.drawdown_pause_pct = float(drawdown_pause_pct)
+        self.liquidity_floor_adv = float(liquidity_floor_adv)
+        self._peak_equity = 0.0
+
+    # ------------------------------------------------------------- gates
+    def _hmm_high_vol(self, pred_date) -> bool:
+        """Cross-sectional mean HMM high-vol regime probability >= threshold."""
+        try:
+            from qlib.data import D
+
+            feat = D.features(D.instruments("all"), ["$sp_hmm_p_regime1"],
+                              start_time=pred_date, end_time=pred_date)
+            if feat is None or len(feat) == 0:
+                return False
+            p = feat["$sp_hmm_p_regime1"].dropna()
+            if len(p) == 0:
+                return False
+            return float(p.mean()) >= self.hmm_pause_pct
+        except Exception:
+            return False
+
+    def _drawdown_active(self, equity: float) -> bool:
+        if self.drawdown_pause_pct <= 0:
+            return False
+        self._peak_equity = max(self._peak_equity, equity)
+        if self._peak_equity <= 0:
+            return False
+        dd = (self._peak_equity - equity) / self._peak_equity * 100.0
+        return dd >= self.drawdown_pause_pct
+
+    def _illiquid(self, codes, asof) -> Dict[str, bool]:
+        if self.liquidity_floor_adv <= 0 or not codes:
+            return {}
+        from tac_qlib.risk_limits import dollar_adv
+
+        adv = dollar_adv(codes, market="US", asof=asof, lookback=20)
+        return {c: adv.get(str(c).upper(), 0.0) < self.liquidity_floor_adv for c in codes}
+
+    # ------------------------------------------------------------- decision
+    def generate_trade_decision(self, execute_result=None):
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
+        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
+        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
+        if pred_score is None:
+            return TradeDecisionWO([], self)
+        if isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+
+        current_temp = copy.deepcopy(self.trade_position)
+        assert isinstance(current_temp, Position)
+        held = {c for c in current_temp.get_stock_list() if abs(current_temp.get_stock_amount(c)) > 1e-6}
+
+        equity = current_temp.get_cash()
+        for code in held:
+            mark = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=1
+            )
+            if mark is not None and np.isfinite(mark):
+                equity += abs(current_temp.get_stock_amount(code)) * mark
+
+        hmm_pause = self._hmm_high_vol(str(pd.Timestamp(pred_start_time).date()))
+        dd_pause = self._drawdown_active(equity)
+        buys_paused = hmm_pause or dd_pause
+
+        pred_score = pred_score.copy()
+        if buys_paused or self.liquidity_floor_adv > 0:
+            new_codes = [c for c in pred_score.index if c not in held]
+            illiquid = self._illiquid(new_codes, str(pd.Timestamp(pred_start_time).date()))
+            for code in new_codes:
+                if buys_paused or illiquid.get(code, False):
+                    pred_score[code] = -1e9  # cannot enter today
+
+        return super().generate_trade_decision(execute_result)

code/tac-qlib/tac_qlib/contrib/strategy/momentum_gate.py

@@ -0,0 +1,91 @@
+"""TopkDropout with a 1-day momentum entry-confirmation gate.
+
+Gates NEW entries on short-term momentum: a name that is not currently held
+may only be bought when its trailing 1-day return is above ``min_momentum``
+(Lag-1 autocorr ~ +0.45 in the time-series study => short-term momentum
+continuation). Held names are never force-sold by this gate — exits stay the
+pure TopkDropout rule.
+
+Implementation: override ``generate_trade_decision`` and zero out the signal
+score of any non-held name that fails the momentum check BEFORE calling the
+base TopkDropout decision, so it can never be selected as a buy candidate.
+This is a clean pre-filter: the rest of the strategy (top-k, n_drop, sizing,
+costs) is untouched.
+
+Wired into a workflow yaml like:
+
+    strategy:
+        class: MomentumGateTopk
+        module_path: tac_qlib.contrib.strategy.momentum_gate
+        kwargs:
+            signal: "<PRED>"
+            topk: 10
+            n_drop: 2
+            only_tradable: true
+            risk_degree: 0.95
+            min_momentum: 0.0
+"""
+
+from __future__ import annotations
+
+import copy
+
+import pandas as pd
+
+from qlib.backtest.decision import TradeDecisionWO
+from qlib.backtest.position import Position
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["MomentumGateTopk"]
+
+
+class MomentumGateTopk(TopkDropoutStrategy):
+    """TopkDropoutStrategy gated on 1-day momentum for new entries."""
+
+    def __init__(self, *, min_momentum: float = 0.0, **kwargs):
+        super().__init__(**kwargs)
+        self.min_momentum = float(min_momentum)
+
+    def _momentum_ok(self, code, trade_start, trade_end) -> bool:
+        """True when the trailing 1-day return is above the momentum floor."""
+        try:
+            cur = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start, end_time=trade_end, direction=1
+            )
+        except Exception:
+            return False
+        if cur is None or cur != cur or cur <= 0:
+            return False
+        prev_start = trade_start - pd.Timedelta(days=5)
+        prev_end = trade_start - pd.Timedelta(seconds=1)
+        prev = self.trade_exchange.get_deal_price(
+            stock_id=code, start_time=prev_start, end_time=prev_end, direction=0
+        )
+        if prev is None or prev != prev or prev <= 0:
+            return False
+        return (cur / prev - 1.0) >= self.min_momentum
+
+    def generate_trade_decision(self, execute_result=None):
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
+        pred_start_time, pred_end_time = self.trade_calendar.get_step_time(trade_step, shift=1)
+        pred_score = self.signal.get_signal(start_time=pred_start_time, end_time=pred_end_time)
+        if pred_score is None:
+            return TradeDecisionWO([], self)
+        if isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+
+        current_temp = copy.deepcopy(self.trade_position)
+        assert isinstance(current_temp, Position)
+        held = set(current_temp.get_stock_list())
+        held = {c for c in held if abs(current_temp.get_stock_amount(c)) > 1e-6}
+
+        # pre-filter: zero the score of non-held names that fail momentum
+        pred_score = pred_score.copy()
+        for code in pred_score.index:
+            if code in held:
+                continue  # never gate exits / re-balancing of held names
+            if not self._momentum_ok(code, trade_start_time, trade_end_time):
+                pred_score[code] = -1e9  # cannot enter today
+
+        return super().generate_trade_decision(execute_result)

code/tac-qlib/tac_qlib/data/config.py

@@ -6,11 +6,10 @@ The lake is a hive-partitioned parquet store (see ``tac-engine/skills/tradeac-la
     ├── market=US/
     │   └── timeframe=1d/
     │       └── symbol=AAPL.parquet        # OHLCV bars: t, date, o, h, l, c, v, n, vw
-    ├── features/                          # indicators, wide format, family tier
+    ├── features/                          # ta-lib indicators, wide format
     │   └── market=US/
     │       └── timeframe=1d/
-    │           ├── family=ta/symbol=AAPL.parquet  # t, sma_5, sma_20, rsi_14, ...
-    │           └── family=sp/symbol=AAPL.parquet  # t, sp_ou_*, sp_hmm_*, ...
+    │           └── symbol=AAPL.parquet    # t, sma_5, sma_20, rsi_14, ...
     ├── calendar.parquet                   # trading days per market
     ├── coverage.parquet                   # per (market,timeframe,symbol) loaded windows
     └── symbols.parquet                    # asset master
@@ -108,34 +107,8 @@ class LakeConfig:
         return self.lake_root / "features" / f"market={self.market}" / f"timeframe={timeframe}"
 
     def features_path(self, timeframe: str, symbol: str) -> Path:
-        # Legacy flat path (no family tier). Prefer `load_features` which
-        # resolves the family=ta|sp partition layout.
         return self.features_dir(timeframe) / f"symbol={str(symbol).upper()}.parquet"
 
-    def load_features(self, timeframe: str, symbol: str) -> pd.DataFrame:
-        """All feature columns for a symbol, merging the `family=ta` and
-        `family=sp` partitions by timestamp. Returns an empty frame when no
-        feature files exist (legacy flat layout falls back transparently)."""
-        sym = str(symbol).upper()
-        frames = []
-        for family in ("ta", "sp"):
-            p = self.features_dir(timeframe) / f"family={family}" / f"symbol={sym}.parquet"
-            if p.exists():
-                frames.append(pd.read_parquet(p))
-        if not frames:
-            flat = self.features_dir(timeframe) / f"symbol={sym}.parquet"
-            if flat.exists():
-                return pd.read_parquet(flat)
-            return pd.DataFrame()
-        if len(frames) == 1:
-            return frames[0]
-        merged = frames[0]
-        for extra in frames[1:]:
-            merged = merged.merge(extra, on="t", how="outer", suffixes=("", "_dup"))
-            for c in [c for c in merged.columns if c.endswith("_dup")]:
-                merged = merged.drop(columns=c)
-        return merged
-
     def calendar_path(self) -> Path:
         return self.lake_root / "calendar.parquet"
 

code/tac-qlib/tac_qlib/data/providers.py

@@ -173,7 +173,8 @@ class LakeFeatureProvider(FeatureProvider):
     def _load_feature_df(self, instrument: str, timeframe: str) -> pd.DataFrame:
         key = (instrument, timeframe)
         if key not in self._feature_cache:
-            self._feature_cache[key] = self.cfg.load_features(timeframe, instrument)
+            p = self.cfg.features_path(timeframe, instrument)
+            self._feature_cache[key] = pd.read_parquet(p) if p.exists() else pd.DataFrame()
         return self._feature_cache[key]
 
     @staticmethod

queue/README.md

@@ -1,69 +0,0 @@
-# TradeAC Experiment Queue — Series 2 (Q12+)
-
-**Purpose.** The next pre-registered batch of experiments, continuing Series 1
-(Q01–Q11, exp 33–43, all executed and folded into `book/CLAIMS.md` /
-`book/EVIDENCE.md`). Each entry targets a still-unproven `HYPOTHESIS` from the
-book or an open question flagged in `CLAIMS.md`/`book/README.md`, and follows the
-Series-1 discipline: one variable changed vs the exp-26 reference, acceptance
-fixed BEFORE the run, sequential execution, trace-first, verify-then-close.
-
-**Reference / control (MUST reproduce first).** exp 26 (`21afc6af…`, mlflow exp
-25) is the campaign baseline; exp 39 (Q07, weekly rebalance) is the best
-construction. Reference config is byte-reproduced in `workflows/exp26/` on the
-`exp/26-…` branch and in this dir's `workflows/*.yaml`.
-
-| Config element | exp-26 reference value |
-|---|---|
-| Universe | 50-ETF panel (`UNIVERSE` below) |
-| Features | compact stochastic 25-field set (no ou/hmm/moments/garch) |
-| Label | `Ref($close,-6)/Ref($close,-1)-1` (5d) |
-| Model | `RankICEnsembleLGBModel`, seeds `42,7,2026,99,123`, lr 0.02, leaves 31, 3000 rounds, ES 200 |
-| Segments | train 2016-01-04..2025-09-01 / valid 2025-09-03..2026-01-03 / test 2026-01-04..2026-08-10 |
-| Strategy | TopkDropout, topk 10, n_drop 1, risk_degree 0.95 |
-| Costs | open 0.0005 / close 0.0015 / min $5, deal $close, SPY benchmark, $1M |
-
-**Reference metrics to beat (EVIDENCE#015):** net_ann +2.13%, net_IR 0.21, gross
-+7.02%, maxDD −7.69%, RankIC 0.0663, RankICIR 0.2545, L/S Sharpe 4.54. Weekly
-(Q07, EVIDENCE#028): net +12.51%, IR 1.24, maxDD −4.13%, ~1.1pp cost drag.
-
-## The queue (ordered by value × feasibility)
-
-| ID | Title / hypothesis | Change vs reference (ONE var) | Acceptance | Config | Ready? |
-|----|--------------------|-------------------------------|------------|--------|--------|
-| Q12 | **22d label + weekly recompute** — the untested combo: Q05's label edge (IC 0.097, RankIC 0.117) with Q07's cost relief | label → 22d AND strategy → weekly (two coupled, explicitly pre-registered) | net_IR > 0.5, net_ann > +5%, cost drag ≤ 2pp | `workflows/q12_label22d_weekly.yaml` | ✅ |
-| Q13 | **Weekly rebalance reproduction on a 2nd window** — Q07 was a single OOS window; reproduce on test 2025-01-02..2025-12-31 before promoting to a live round | segments only (shifted) | net_IR > 0.21, net_ann > +2.13% on the new window | `workflows/q13_weekly_second_window.yaml` | ✅ |
-| Q14 | **Out-of-universe validation** — compact stochastic set generalizes off the 50-ETF panel to a single-stock universe | universe → 30 liquid single names | RankIC > 0.03, ICIR > 0.15, net IR > 0 on stocks | `workflows/q14_out_of_universe.yaml` | ⚠️ needs stock-lake backfill (see design) |
-| Q15 | **5-seed vs single-model clean A/B** — seed-count claim (exp 12 idea, re-validated exp 22–24, never a clean A/B) | seeds → 1 (`2026`) | single-model RankIC/IR < 5-seed ref; net_IR ≥ 0.21 acceptable if ≥ single | `workflows/q15_single_seed.yaml` | ✅ |
-| Q16 | **HMM family added as features** — settles "dropping model-specific (ou,hmm) improves signal" (exp 25 tested OU; hmm-as-feature untested) | features += `sp_hmm_p_regime1,sp_hmm_state` | no improvement: RankIC ≤ 0.0663, net_IR ≤ 0.21 | `workflows/q16_hmm_features.yaml` | ✅ |
-| Q17 | **Realized-moments family added** — settles "moment/volatility families regress" (exp 11 idea, never clean A/B) | features += `sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22` | no improvement: RankIC ≤ 0.0663, net_IR ≤ 0.21 | `workflows/q17_moments_features.yaml` | ✅ |
-| Q18 | **OptimalStopControl clean re-test** — exp 13/14 claim (TopkDropout > stop-control) never re-tested post-reset | strategy → `OptimalStopControl` (exp-13 params) | TopkDropout net_IR ≥ stop-control net_IR; document cost drag | `workflows/q18_optstop.yaml` | ✅ (module verified in venv) |
-| Q19 | **Martingale / variance-ratio study close-out** — exp 19 never closed; VR<1 at 5–20d on clean lake | ad-hoc script (no qrun) | VR stats + drift decomposition on 50-ETF panel | `designs/q19_martingale_vr.md` | ✅ script |
-| Q20 | **Effective independent names (≈4)** — eigenvalue analysis on clean-lake covariance | ad-hoc script | eigenvalue spectrum + effective-rank count | `designs/q20_effective_names.md` | ✅ script |
-
-### Deferred (methodology / infra, P3)
-- Purged / walk-forward CV (was queue's old Q12) — methodology, not an alpha lever.
-- PSI-based drift-aware retraining cadence — needs a drift-gate module + a retrain decision rule.
-- No-trade buffer band / notional-vs-qty sizing — siblings of Q12/Q13; queue only if weekly reproduces.
-- Macro/drift overlays (SPY>200d regime gate, momentum tilt) — needs new data pipeline.
-
-## Execution protocol (per queued run)
-
-1. **Validate the lake first** (`validate_lake_dataset` + `rd_status`) — clean-lake lesson: silent NaN-drops and hollow coverage invalidate a run. Q14 additionally requires backfilling the single-stock universe (bars + sp/ta features, full range, explicit `start`/`end`).
-2. **Trace before running** (`rd_trace_start` with the hypothesis as `rational`, fresh `experiment_name`, `evolved_from=auto`).
-3. **Run** `rd_run_workflow config_path=<abs path to the queue YAML> experiment_name=<fresh name>` — `wait=false`, poll `rd_exp_get_run` until `FINISHED`.
-4. **Verify against acceptance** via `rd_exp_result` (headline + backtest risk).
-5. **Finish the trace** (`rd_trace_finish` with `metrics` + `evaluation`), snapshot any changed contrib modules.
-6. **Report to the book** — PROVE/REFUTE → update `book/CLAIMS.md` + `book/EVIDENCE.md`.
-
-Sequential execution only (concurrent runs hang — chat-ideas.md ops lesson). Any
-custom strategy/module changed here must be copied into the venv site-packages
-snapshot before `rd_run_workflow` can import it (see `/app/AGENTS.md`). As of
-2026-08-20 `WeeklyRebalanceDropoutStrategy` and `OptimalStopControl` are verified
-in sync with the venv snapshot; the lake already persists the `sp_hmm_*` and
-`sp_moments` families on the 50-ETF panel.
-
-## Provenance
-
-Mined 2026-08-20 from `book/CLAIMS.md`, `book/EVIDENCE.md`, `book/README.md`,
-`book/references/chat-ideas.md`, and Series-1 `queue/` (Q01–Q11, executed exp
-33–43). Reference numbers are post-clean-lake (exp 21+).

queue/designs/q19_martingale_vr.md

@@ -1,26 +0,0 @@
-# QUEUE-19 — Martingale / variance-ratio study close-out (no qrun)
-
-**Status:** QUEUED · **Priority:** P2 · **Effort:** ad-hoc script under `book/data/`
-
-## Hypothesis (settle)
-Assets are submartingales long-horizon / mean-reverting short-horizon
-(`VR < 1` at 5–20d). CLAIMS.md marks this HYPOTHESIS (chat-derived martingale
-study; exp 19 was opened but never closed). It is a market-structure claim, not a
-trading claim — settle it with a clean-lake script, then close exp 19 or open a
-scripted EVIDENCE entry.
-
-## Method (persist everything under `book/data/evidence/q19-vr/`)
-1. Load the 50-ETF panel 1d bars from the lake for 2015-01-01..2026-08-19.
-2. Compute the Lo–MacKinlay variance ratio at horizons 5 / 10 / 20d per symbol,
-   with heteroskedasticity-robust z-stats.
-3. Report: per-horizon VR distribution, fraction of symbols with VR < 1 and the
-   z-significance, pooled drift vs daily variance (submartingale check).
-4. Cross-check the pooled `sp_trend_slope_5` regression beta claim (β ≈ −0.53,
-   t ≈ −24) on the clean lake.
-5. Write `VR_stats.csv` + a one-page summary into the evidence dir.
-
-## Acceptance
-- VR < 1 at 5–20d for a material fraction of the panel with |z| > 2 → supports
-  the mean-reversion HYPOTHESIS; else mark REFUTED or REFERENCED.
-- The result updates CLAIMS.md's "Assets are submartingales…" row and closes the
-  exp-19 open thread.

queue/designs/q20_effective_names.md

@@ -1,22 +0,0 @@
-# QUEUE-20 — Effective independent names in the 50-ETF book (no qrun)
-
-**Status:** QUEUED · **Priority:** P2 · **Effort:** ad-hoc script under `book/data/`
-
-## Hypothesis (settle)
-The 50-ETF book has only ~4 effective independent names (CLAIMS.md HYPOTHESIS,
-chat-derived eigenvalue analysis, pre-reset). This is a concentration/diversification
-claim with direct sizing relevance; verify it on the clean lake.
-
-## Method (persist everything under `book/data/evidence/q20-effective-names/`)
-1. Load the 50-ETF panel 1d returns from the lake for the test window 2026-01-04..2026-08-10.
-2. Standardize returns; compute the correlation matrix and its eigendecomposition.
-3. Count eigenvalues above the Marchenko–Pastur bound (N=50, T≈150) and report the
-   cumulative-variance share of the top k components.
-4. Effective-rank measures: participation ratio `(Σλ)² / Σλ²` and cumulative 80%
-   variance count.
-5. Write `eigenanalysis.csv` + a one-page summary.
-
-## Acceptance
-- If effective rank ≈ 4 (top-4 explain ~80%+ variance), the concentration claim is
-  PROVEN and feeds chapter 08 sizing guidance (why topk 10→20 adds no breadth).
-- If effective rank is much larger, mark the claim REFUTED.

queue/workflows/q12_label22d_weekly.yaml

@@ -1,105 +0,0 @@
-# QUEUE-12 — Long-horizon label (22d) + weekly recompute construction.
-# Untested combination from book/CLAIMS.md open questions: Q05 (exp 37) proved the
-# 22d label has the strongest signal (IC 0.097, RankIC 0.117) but daily turnover
-# killed the book (net -4.60%); Q07 (exp 39) proved weekly recompute is the cost
-# lever (net +12.51%). Hypothesis: pairing them monetizes the label edge.
-# Change vs exp-26 reference: label 5d -> 22d AND strategy -> WeeklyRebalanceDropoutStrategy.
-# Acceptance: net_IR > 0.5, net_ann > +5%, cost drag <= 2pp.
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q12_label22d_weekly.yaml \
-#        experiment_name=tac-rd-q12-label22d-weekly
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q12-label22d-weekly" }
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-10
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-23)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
-                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
-            segments:
-                train: [2016-01-04, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: WeeklyRebalanceDropoutStrategy
-                      module_path: tac_qlib.contrib.strategy.weekly_rebalance
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d

queue/workflows/q13_weekly_second_window.yaml

@@ -1,106 +0,0 @@
-# QUEUE-13 — Weekly rebalance reproduction on a second OOS window.
-# Q07 (exp 39) proved weekly recompute on test 2026-01-04..2026-08-10 (net +12.51%,
-# IR 1.24) but that is a single OOS window. Before promoting the weekly construction
-# to a live round, reproduce it on a disjoint window: test 2025-01-02..2025-12-31
-# with train/valid shifted to end 2024.
-# Change vs exp-26 reference: segments shifted only (train ends 2024-08, test = 2025);
-# strategy is the SAME weekly recompute as exp 39. Label stays 5d.
-# Acceptance: net_IR > 0.21 AND net_ann > +2.13% on the 2025 window.
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q13_weekly_second_window.yaml \
-#        experiment_name=tac-rd-q13-weekly-second-window
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q13-weekly-second-window" }
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2025-12-31
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2024-08-30
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
-                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2024-08-30" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2024-08-30" } }
-                        - { class: Fillna, kwargs: {} }
-            segments:
-                train: [2016-01-04, 2024-08-30]
-                valid: [2024-09-03, 2024-12-31]
-                test: [2025-01-02, 2025-12-31]
-
-    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: WeeklyRebalanceDropoutStrategy
-                      module_path: tac_qlib.contrib.strategy.weekly_rebalance
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
-                  backtest:
-                      start_time: 2025-01-02
-                      end_time: 2025-12-31
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d

queue/workflows/q14_out_of_universe.yaml

@@ -1,107 +0,0 @@
-# QUEUE-14 — Out-of-universe validation: compact stochastic set on single-stock names.
-# The 50-ETF panel results (compact feature set, RankIC 0.0663) are panel-specific;
-# book/CLAIMS.md marks "generalizes to other universes" HYPOTHESIS - TODO(evidence-needed).
-# Change vs exp-26 reference: universe -> 30 liquid US single-stock names.
-# PREREQUISITE: backfill lake bars + sp/ta features for these symbols (full range,
-# explicit start/end) — the stock panel currently has only ~180d of data (2025-12-01+).
-# Backfill: get_lake_bars symbols=... start=2000-01-03 then
-#   get_lake_sp symbol=<s> start=2000-01-03 end=<today> fit_end=<train-end> persist=true
-# Acceptance: RankIC > 0.03, ICIR > 0.15, net IR > 0 on the stock universe.
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q14_out_of_universe.yaml \
-#        experiment_name=tac-rd-q14-out-of-universe
-{%- set LAKE = TAC_LAKE_DIR %}
-{%- set UNIVERSE = "AAPL,MSFT,NVDA,AMZN,GOOGL,META,TSLA,AVGO,AMD,JPM,UNH,PG,JNJ,MA,V,WMT,DIS,HD,KO,PEP,BAC,XOM,MCD,ABBV,COST,CRM,NFLX,ORCL,IBM,T" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
-
-qlib_init:
-    provider_uri: "{{ LAKE }}"
-    region: us
-    expression_cache: null
-    dataset_cache: null
-    calendar_provider:
-        class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    instrument_provider:
-        class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
-    feature_provider:
-        class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
-    exp_manager:
-        class: MLflowExpManager
-        module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q14-out-of-universe" }
-
-task:
-    model:
-        class: RankICEnsembleLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
-        kwargs:
-            loss: mse
-            learning_rate: 0.02
-            num_leaves: 31
-            n_estimators: 3000
-            num_boost_round: 3000
-            early_stopping_rounds: 200
-            min_data_in_leaf: 20
-            lambda_l2: 0.5
-            colsample_bytree: 0.8
-            subsample: 0.8
-            subsample_freq: 1
-            reg_alpha: 0.1
-            reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
-
-    dataset:
-        class: DatasetH
-        module_path: qlib.data.dataset
-        kwargs:
-            handler:
-                class: TACHandler
-                module_path: tac_qlib.contrib.data.handler
-                kwargs:
-                    instruments: "{{ UNIVERSE }}"
-                    start_time: 2015-01-03
-                    end_time: 2026-08-10
-                    fit_start_time: 2016-01-04
-                    fit_end_time: 2025-09-01
-                    freq: day
-                    lake_root: "{{ LAKE }}"
-                    market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
-                    infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
-            segments:
-                train: [2016-01-04, 2025-09-01]
-                valid: [2025-09-03, 2026-01-03]
-                test: [2026-01-04, 2026-08-10]
-
-    record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
-        - class: PortAnaRecord
-          module_path: qlib.workflow.record_temp
-          kwargs:
-              config:
-                  strategy:
-                      class: TopkDropoutStrategy
-                      module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
-                  backtest:
-                      start_time: 2026-01-04
-                      end_time: 2026-08-10
-                      account: 1000000
-                      benchmark: SPY
-                      exchange_kwargs:
-                          codes: "{{ UNIVERSE }}"
-                          deal_price: $close
-                          freq: day
-                          open_cost: 0.0005
-                          close_cost: 0.0015
-                          min_cost: 5.0
-              risk_analysis_freq: 1d

workflows/ablate_baseline_all_sp_fields.yaml

@@ -0,0 +1,133 @@
+# -----------------------------------------------------------------------------
+# ABLATION A (baseline): LightGBM with RankIC early-stopping on the 50-ETF SP-5d
+# panel, using ALL 24 sp_* feature columns (ou,hmm,jump,har,trend,hurst,
+# signature). Copy of the canonical workflow_lgb_sp5d_rankic.yaml with a
+# distinct experiment name so the ablation runs are isolated.
+#
+# Run:
+#   rd_run_workflow config_path=tac-qlib/workflows/ablate_baseline_all_sp_fields.yaml \
+#       experiment_name=tac-rd-rank-ablate
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_ou_zscore,sp_ou_half_life,sp_ou_revert,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-rank-ablate"
+
+task:
+    model:
+        class: RankICLGBModel
+        module_path: tac_qlib.contrib.model.rank_gbdt
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seed: 42
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-10
+                    fit_start_time: 2015-01-03
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2015-01-03, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/ablate_generic_only_sp_fields.yaml

@@ -0,0 +1,134 @@
+# -----------------------------------------------------------------------------
+# ABLATION B (generic-only): same panel/model as the baseline, but feature
+# fields restricted to the model-free / generic stochastic-process families
+# (jump,har,trend,hurst,signature). Drops the model-specific ou (OU/AR-1
+# half-life) and hmm (2-state regime) families to test whether the generic
+# families alone dominate the rank dimension.
+#
+# Run:
+#   rd_run_workflow config_path=tac-qlib/workflows/ablate_generic_only_sp_fields.yaml \
+#       experiment_name=tac-rd-rank-ablate
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-rank-ablate"
+
+task:
+    model:
+        class: RankICLGBModel
+        module_path: tac_qlib.contrib.model.rank_gbdt
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seed: 42
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-10
+                    fit_start_time: 2015-01-03
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2015-01-03, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp12_isolation_ensemble.yaml

@@ -0,0 +1,141 @@
+# -----------------------------------------------------------------------------
+# ISOLATION: multi-seed RankIC ensemble, ablate-B generic-only feature set.
+#
+# Isolates the ensemble effect on the SP-5d rank signal. Same panel, segments,
+# history (full backfilled 2016+) and feature set as the exp-9 ablate-B winner
+# (generic-only sp_* families: jump,har,trend,hurst,signature), but replaces the
+# single RankICLGBModel with a 5-seed RankICEnsembleLGBModel (42,7,2026,99,123)
+# that averages per-day predictions.
+#
+# Differs from exp-15 (tac-rd-rank-ensemble, mlflow exp 15) ONLY by dropping the
+# TA subset (rsi_14,roc_10,macd_hist,willr_14,atr_14) and the inter-asset xr_*
+# features, so any change vs exp-15 is attributable to the feature set alone,
+# and any change vs exp-9 is attributable to the ensemble + full history alone.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp12_isolation_ensemble.yaml \
+#       experiment_name=tac-rd-rank-ensemble-isolated
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///mlruns.db"
+            default_exp_name: "tac-rd-rank-ensemble-isolated"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp18-risk-limit/a_baseline.yaml

@@ -0,0 +1,141 @@
+# -----------------------------------------------------------------------------
+# EXP 18 - Risk-limit control: reference model + TopkDropout baseline (A).
+#
+# Signal/model identical to the reference (tac-rd-rank-ensemble-isolated,
+# run 0cea66d9...): RankICEnsembleLGBModel (parallel, 5 seeds) on the 50-ETF
+# SP-5d panel, test 2026-01-04..2026-08-10. This workflow reproduces the
+# unconstrained TopkDropout baseline net-of-cost so the risk-limited variant
+# (same pred, liquidity/size/concentration caps) can be compared 1:1.
+#
+# The risk_limits spec itself is applied via rd_backtest / rd_strategy_targets
+# (tool-level param, not a YAML key); this run records the unconstrained
+# baseline that the limit A/B is measured against.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp18-risk-limit/a_baseline.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            parallel: 5
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp20-risk-limit-improve/r0_5seed_baseline.yaml

@@ -1,34 +1,47 @@
-# QUEUE-17 — Realized-moments family added to the compact set.
-# CLAIMS.md HYPOTHESIS: "Adding moment/volatility families regresses the signal"
-# (idea: pre-clean-lake exp 11). M1 momentum bundle (exp 29) and M3 GARCH (exp 31)
-# were refuted post-reset; the realized-moments family (sp_rskew/sp_rkurt/sp_dsv)
-# has NOT been clean A/B'd. This run adds the moments columns to the compact set.
-# Change vs exp-26 reference: features += sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22.
-# Acceptance (prune-hypothesis): no improvement — RankIC <= 0.0663, net_IR <= 0.21.
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q17_moments_features.yaml \
-#        experiment_name=tac-rd-q17-moments-features
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_5,sp_dsv_22" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
     region: us
     expression_cache: null
     dataset_cache: null
+
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q17-moments-features" }
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
 
 task:
     model:
@@ -49,6 +62,7 @@ task:
             reg_alpha: 0.1
             reg_lambda: 1.0
             seeds: "42,7,2026,99,123"
+            parallel: 5
 
     dataset:
         class: DatasetH
@@ -60,28 +74,39 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                     fit_start_time: 2016-01-04
                     fit_end_time: 2025-09-01
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
                     label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                     infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
             segments:
                 train: [2016-01-04, 2025-09-01]
                 valid: [2025-09-03, 2026-01-03]
                 test: [2026-01-04, 2026-08-10]
 
     record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs:
@@ -89,7 +114,12 @@ task:
                   strategy:
                       class: TopkDropoutStrategy
                       module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
                   backtest:
                       start_time: 2026-01-04
                       end_time: 2026-08-10
@@ -102,4 +132,4 @@ task:
                           open_cost: 0.0005
                           close_cost: 0.0015
                           min_cost: 5.0
-              risk_analysis_freq: 1d
+              risk_analysis_freq: 1d

workflows/exp20-risk-limit-improve/r0_det_baseline.yaml

@@ -1,34 +1,47 @@
-# QUEUE-16 — HMM family added as model features to the compact set.
-# CLAIMS.md HYPOTHESIS: "Dropping model-specific feature families (ou, hmm)
-# improves the rank signal" — exp 25 cleanly tested OU (adding it hurts: IC 0.0511->0.0343);
-# hmm-as-features has NOT been clean A/B'd post-reset (exp 42 tested hmm as an entry
-# GATE overlay, refuted). This run adds the hmm family columns to the compact set.
-# Change vs exp-26 reference: features += sp_hmm_p_regime1, sp_hmm_state.
-# Acceptance (prune-hypothesis): no improvement — RankIC <= 0.0663, net_IR <= 0.21.
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q16_hmm_features.yaml \
-#        experiment_name=tac-rd-q16-hmm-features
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_hmm_p_regime1,sp_hmm_state" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
     region: us
     expression_cache: null
     dataset_cache: null
+
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q16-hmm-features" }
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
 
 task:
     model:
@@ -49,6 +62,7 @@ task:
             reg_alpha: 0.1
             reg_lambda: 1.0
             seeds: "42,7,2026,99,123"
+            parallel: 1
 
     dataset:
         class: DatasetH
@@ -60,28 +74,39 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                     fit_start_time: 2016-01-04
                     fit_end_time: 2025-09-01
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
                     label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                     infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
             segments:
                 train: [2016-01-04, 2025-09-01]
                 valid: [2025-09-03, 2026-01-03]
                 test: [2026-01-04, 2026-08-10]
 
     record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs:
@@ -89,7 +114,12 @@ task:
                   strategy:
                       class: TopkDropoutStrategy
                       module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
                   backtest:
                       start_time: 2026-01-04
                       end_time: 2026-08-10
@@ -102,4 +132,4 @@ task:
                           open_cost: 0.0005
                           close_cost: 0.0015
                           min_cost: 5.0
-              risk_analysis_freq: 1d
+              risk_analysis_freq: 1d

workflows/exp20-risk-limit-improve/r1_2seed.yaml

@@ -1,33 +1,47 @@
-# QUEUE-15 — 5-seed vs single-model clean A/B on the compact stochastic set.
-# CLAIMS.md HYPOTHESIS: "5-seed RankIC ensemble raises performance vs single model
-# on ablated set" — pre-clean-lake exp 12 idea, re-validated directionally by exp
-# 22–24, never a clean A/B post-reset. Seed count is load-bearing (exp 28: 2<5).
-# Change vs exp-26 reference: seeds "42,7,2026,99,123" -> single seed "2026".
-# Acceptance: single-model RankIC < 0.0663, net_IR < 0.21 (ensemble beats single).
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q15_single_seed.yaml \
-#        experiment_name=tac-rd-q15-single-seed
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
     region: us
     expression_cache: null
     dataset_cache: null
+
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q15-single-seed" }
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
 
 task:
     model:
@@ -47,7 +61,8 @@ task:
             subsample_freq: 1
             reg_alpha: 0.1
             reg_lambda: 1.0
-            seeds: "2026"
+            seeds: "42,7"
+            parallel: 2
 
     dataset:
         class: DatasetH
@@ -59,28 +74,39 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                     fit_start_time: 2016-01-04
                     fit_end_time: 2025-09-01
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
                     label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                     infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
             segments:
                 train: [2016-01-04, 2025-09-01]
                 valid: [2025-09-03, 2026-01-03]
                 test: [2026-01-04, 2026-08-10]
 
     record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs:
@@ -88,7 +114,12 @@ task:
                   strategy:
                       class: TopkDropoutStrategy
                       module_path: qlib.contrib.strategy
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 1, only_tradable: true, risk_degree: 0.95 }
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
                   backtest:
                       start_time: 2026-01-04
                       end_time: 2026-08-10
@@ -101,4 +132,4 @@ task:
                           open_cost: 0.0005
                           close_cost: 0.0015
                           min_cost: 5.0
-              risk_analysis_freq: 1d
+              risk_analysis_freq: 1d

workflows/exp20-risk-limit-improve/r2_momentum.yaml

@@ -0,0 +1,136 @@
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            parallel: 5
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: MomentumGateTopk
+                      module_path: tac_qlib.contrib.strategy.momentum_gate
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          min_momentum: 0.0
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp20-risk-limit-improve/r3_hmm_risk.yaml

@@ -0,0 +1,138 @@
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            parallel: 5
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: HmmRiskTopk
+                      module_path: tac_qlib.contrib.strategy.hmm_risk
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          hmm_pause_pct: 0.70
+                          drawdown_pause_pct: 8.0
+                          liquidity_floor_adv: 5000000
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp20-risk-limit-improve/r4_rolling_ic.yaml

@@ -0,0 +1,137 @@
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
+{%- set LAKE = TAC_LAKE_DIR %}
+{%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+
+qlib_init:
+    provider_uri: "{{ LAKE }}"
+    region: us
+    expression_cache: null
+    dataset_cache: null
+
+    calendar_provider:
+        class: tac_qlib.data.providers.LakeCalendarProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+    instrument_provider:
+        class: tac_qlib.data.providers.LakeInstrumentProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
+    feature_provider:
+        class: tac_qlib.data.providers.LakeFeatureProvider
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
+    exp_manager:
+        class: MLflowExpManager
+        module_path: qlib.workflow.expm
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
+
+task:
+    model:
+        class: RankICEnsembleLGBModel
+        module_path: tac_qlib.contrib.model.rank_ensemble
+        kwargs:
+            loss: mse
+            learning_rate: 0.02
+            num_leaves: 31
+            n_estimators: 3000
+            num_boost_round: 3000
+            early_stopping_rounds: 200
+            min_data_in_leaf: 20
+            lambda_l2: 0.5
+            colsample_bytree: 0.8
+            subsample: 0.8
+            subsample_freq: 1
+            reg_alpha: 0.1
+            reg_lambda: 1.0
+            seeds: "42,7,2026,99,123"
+            weight_mode: rolling_ic
+            rolling_ic_window: 21
+            parallel: 5
+
+    dataset:
+        class: DatasetH
+        module_path: qlib.data.dataset
+        kwargs:
+            handler:
+                class: TACHandler
+                module_path: tac_qlib.contrib.data.handler
+                kwargs:
+                    instruments: "{{ UNIVERSE }}"
+                    start_time: 2015-01-03
+                    end_time: 2026-08-14
+                    fit_start_time: 2016-01-04
+                    fit_end_time: 2025-09-01
+                    freq: day
+                    lake_root: "{{ LAKE }}"
+                    market: US
+                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
+                    infer_processors:
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
+            segments:
+                train: [2016-01-04, 2025-09-01]
+                valid: [2025-09-03, 2026-01-03]
+                test: [2026-01-04, 2026-08-10]
+
+    record:
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
+        - class: PortAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              config:
+                  strategy:
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
+                  backtest:
+                      start_time: 2026-01-04
+                      end_time: 2026-08-10
+                      account: 1000000
+                      benchmark: SPY
+                      exchange_kwargs:
+                          codes: "{{ UNIVERSE }}"
+                          deal_price: $close
+                          freq: day
+                          open_cost: 0.0005
+                          close_cost: 0.0015
+                          min_cost: 5.0
+              risk_analysis_freq: 1d

workflows/exp20-risk-limit-improve/r5_ma3_ewma.yaml

@@ -1,35 +1,47 @@
-# QUEUE-18 — OptimalStopControl clean re-test vs TopkDropout (exp 13/14 claim).
-# CLAIMS.md HYPOTHESIS: "TopkDropout beats stochastic-control OptimalStopControl on
-# the ensemble signal" — exp 13/14 were pre-clean-lake; never re-tested post-reset.
-# Same compact signal as the exp-26 reference; ONLY the strategy changes to
-# OptimalStopControl with exp-13 params (entry 0.85 / exit 0.7 / hold 10 / sl -0.08).
-# PREREQUISITE: tac_qlib/contrib/strategy/optimal_stop.py must be synced to the venv
-# site-packages snapshot before running (see /app/AGENTS.md).
-# Acceptance: TopkDropout net_IR >= stop-control net_IR; document cost drag of both.
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q18_optstop.yaml \
-#        experiment_name=tac-rd-q18-optstop
+# -----------------------------------------------------------------------------
+# EXP 20 - R1: 2-seed ensemble (seeds 42,7), TopkDropout baseline.
+#
+# Runtime cut: 2 seeds instead of 5. Everything else identical to the reference
+# (test 2026-01-04..2026-08-10, SPY, costs 5bp/15bp). Measures whether the
+# 2-seed ensemble keeps the reference quality at ~2/5 the training time.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp20-risk-limit-improve/r1_2seed.yaml \
+#       experiment_name=tac-rd-risk-limit
+# -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sma_3,ema_3" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
     region: us
     expression_cache: null
     dataset_cache: null
+
     calendar_provider:
         class: tac_qlib.data.providers.LakeCalendarProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
     instrument_provider:
         class: tac_qlib.data.providers.LakeInstrumentProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US, markets: {} }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+            markets: {}
     feature_provider:
         class: tac_qlib.data.providers.LakeFeatureProvider
-        kwargs: { lake_root: "{{ LAKE }}", market: US }
+        kwargs:
+            lake_root: "{{ LAKE }}"
+            market: US
+
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q18-optstop" }
+        kwargs:
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
+            default_exp_name: "tac-rd-risk-limit"
 
 task:
     model:
@@ -50,6 +62,7 @@ task:
             reg_alpha: 0.1
             reg_lambda: 1.0
             seeds: "42,7,2026,99,123"
+            parallel: 5
 
     dataset:
         class: DatasetH
@@ -61,36 +74,52 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                     fit_start_time: 2016-01-04
                     fit_end_time: 2025-09-01
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
                     label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                     infer_processors:
-                        - { class: DropAllNaN, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: ProcessInf, kwargs: {} }
-                        - { class: CSRankNorm, kwargs: {} }
-                        - { class: ZScoreNorm, kwargs: { fit_start_time: "2016-01-04", fit_end_time: "2025-09-01" } }
-                        - { class: Fillna, kwargs: {} }
+                        - class: DropAllNaN
+                          kwargs: {}
+                        - class: ProcessInf
+                          kwargs: {}
+                        - class: CSRankNorm
+                          kwargs: {}
+                        - class: ZScoreNorm
+                          kwargs: {}
+                        - class: Fillna
+                          kwargs: {}
             segments:
                 train: [2016-01-04, 2025-09-01]
                 valid: [2025-09-03, 2026-01-03]
                 test: [2026-01-04, 2026-08-10]
 
     record:
-        - { class: SignalRecord, module_path: qlib.workflow.record_temp, kwargs: {} }
-        - { class: SigAnaRecord, module_path: qlib.workflow.record_temp, kwargs: { ana_long_short: true, ann_scaler: 252 } }
+        - class: SignalRecord
+          module_path: qlib.workflow.record_temp
+          kwargs: {}
+        - class: SigAnaRecord
+          module_path: qlib.workflow.record_temp
+          kwargs:
+              ana_long_short: true
+              ann_scaler: 252
         - class: PortAnaRecord
           module_path: qlib.workflow.record_temp
           kwargs:
               config:
                   strategy:
-                      class: OptimalStopControl
-                      module_path: tac_qlib.contrib.strategy.optimal_stop
-                      kwargs: { signal: "<PRED>", topk: 10, entry_pct: 0.85, exit_pct: 0.7, max_hold_days: 10, min_hold_days: 2, sl: -0.08 }
+                      class: TopkDropoutStrategy
+                      module_path: qlib.contrib.strategy
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          n_drop: 2
+                          only_tradable: true
+                          risk_degree: 0.95
                   backtest:
                       start_time: 2026-01-04
                       end_time: 2026-08-10
@@ -103,4 +132,4 @@ task:
                           open_cost: 0.0005
                           close_cost: 0.0015
                           min_cost: 5.0
-              risk_analysis_freq: 1d
+              risk_analysis_freq: 1d