finish experiment 46 (exp/46-q15-the-5-seed-rankicensemblelgbmodel-sh)

code/MANIFEST.txt

@@ -1,27 +1,31 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : e660b4f2dd7c521615c54a142eec9266837f2e64
+# parent repo HEAD : bba17bd401cd9cca714c329f7eb3ab71c36a490b
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):
   1b6298c4a5652f2e863cbdc385a1014a570fcd59  tac-qlib/tac_qlib/contrib/__init__.py
-  b5e28b7c0a10ab553eaa6303013a880731742378  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
+  b419ee55ed455a1c45423d1c9025ca5cc0a98576  tac-qlib/tac_qlib/contrib/__pycache__/__init__.cpython-312.pyc
   c76a9f17f680e74eea766eff27f7624359749ed6  tac-qlib/tac_qlib/contrib/data/__init__.py
-  715ab312125a446af751b928fe41cf41b99ffcd0  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
+  2f6c67620aa2f9e6aaaef3369361d9b3eac3d6ca  tac-qlib/tac_qlib/contrib/data/__pycache__/__init__.cpython-312.pyc
-  a82a6a236db93097d48748e541c2cf9caa4e48b5  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
+  fdd5923a70a399e8680913593ff111641947898e  tac-qlib/tac_qlib/contrib/data/__pycache__/handler.cpython-312.pyc
   0dd25ef161c6e0f15eafc84886e7e1381deb38c3  tac-qlib/tac_qlib/contrib/data/handler.py
   b151d139a0dcde87d74b21e7c4b729176ba5c39b  tac-qlib/tac_qlib/contrib/model/__init__.py
-  483221cf1d5bad779d3cf9505269b7fb0b3f165d  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
+  08dec87ccdf6bb5d2cf611ca3032a4280aaab8cf  tac-qlib/tac_qlib/contrib/model/__pycache__/__init__.cpython-312.pyc
-  1286dec07a861f25691b24f71ecc22d8eb3537df  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
+  6fb61946ea9a83dfb560de3717f5fbf482c4c00e  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_ensemble.cpython-312.pyc
-  5185764bd55dbc63d16582bfcb6adc11b7e6d342  tac-qlib/tac_qlib/contrib/model/__pycache__/rank_gbdt.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
-  ccfe7d554989aa7f3e5a2128ae663e51b2207149  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
+  d03e6611338918d4aac5eea4adf26f85a3763652  tac-qlib/tac_qlib/contrib/model/rank_gbdt.py
-  4afcf9058231111c412925f4c4b84e81d656db87  tac-qlib/tac_qlib/contrib/strategy/__init__.py
+  c4ef84ffda2a611262412fe1127689c667f3d0c1  tac-qlib/tac_qlib/contrib/strategy/__init__.py
-  13a8e4a41ce9afde97a55756d666d3ff5cbbec0e  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
+  6ad10c2ebe37c16417e67c7aeb731ad1fcb6da2f  tac-qlib/tac_qlib/contrib/strategy/__pycache__/__init__.cpython-312.pyc
-  0bb5804a79611c66bc25988226ca0f1cdbe1a7eb  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  8d684b3216b040071d9ee4fa920a0e0c7486d278  tac-qlib/tac_qlib/contrib/strategy/__pycache__/optimal_stop.cpython-312.pyc
+  896ef74ae47bcd1ed388e1e5d9c8d70c28097fe9  tac-qlib/tac_qlib/contrib/strategy/kelly_dropout.py
   79aaad9e39fcc740a773f4f63c512ce1086cfde0  tac-qlib/tac_qlib/contrib/strategy/optimal_stop.py
+  5b9acfb4340111b204249add7760bd53c6ae03f1  tac-qlib/tac_qlib/contrib/strategy/regime_gate.py
+  aa1ee880d52ceb5821d65973962099c2254f710a  tac-qlib/tac_qlib/contrib/strategy/top_bottom.py
+  fe60bacdfedd48617863be31f24b7c7daebfac5a  tac-qlib/tac_qlib/contrib/strategy/weekly_rebalance.py
   92e6e90eb0cd0a25142034560f27adb6b705b1a8  tac-qlib/tac_qlib/data/__init__.py
-  3cbc0686e6f863d306d93c589a607a5bdb7201f2  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
+  7c4e6c345fad1978efe8860c0d977d0c02d6f8d9  tac-qlib/tac_qlib/data/__pycache__/__init__.cpython-312.pyc
-  46bcdbcc173ff3a6281fed33d10c1bcac96876b0  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
+  99e602392d51663cb06d5c425000b1ed1e5a916b  tac-qlib/tac_qlib/data/__pycache__/config.cpython-312.pyc
-  6df4f88af22ab4c026c14ef1835f2e630cdf850c  tac-qlib/tac_qlib/data/__pycache__/providers.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

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

@@ -53,23 +53,61 @@ 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))])
-    vals = []
+    gid = np.repeat(np.arange(len(group)), group.astype(int))
-    for i in range(len(group)):
+    rp = _group_averaged_rank(preds, gid, offs)
-        s = slice(offs[i], offs[i + 1])
+    rl = _group_averaged_rank(labels, gid, offs)
-        p, l = preds[s], labels[s]
+    n_g = group.astype(float)
-        if len(p) < 3 or np.std(p) == 0 or np.std(l) == 0:
+    s_p = np.bincount(gid, weights=rp)
-            continue
+    s_l = np.bincount(gid, weights=rl)
-        vals.append(np.corrcoef(pd.Series(p).rank(), pd.Series(l).rank())[0, 1])
+    s_pl = np.bincount(gid, weights=rp * rl)
-    return float(np.mean(vals)) if vals else 0.0
+    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
 
 
 def rankic_feval(preds, dataset):

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

@@ -1,3 +1,13 @@
+from .kelly_dropout import FractionalKellyDropoutStrategy  # noqa: F401
 from .optimal_stop import OptimalStopControl  # noqa: F401
+from .regime_gate import RegimeGateDropoutStrategy  # noqa: F401
+from .top_bottom import TopBottomDropoutStrategy  # noqa: F401
+from .weekly_rebalance import WeeklyRebalanceDropoutStrategy  # noqa: F401
 
-__all__ = ["OptimalStopControl"]
+__all__ = [
+    "OptimalStopControl",
+    "FractionalKellyDropoutStrategy",
+    "WeeklyRebalanceDropoutStrategy",
+    "TopBottomDropoutStrategy",
+    "RegimeGateDropoutStrategy",
+]

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

@@ -0,0 +1,201 @@
+"""Fractional-Kelly dropout strategy for cross-sectional signals.
+
+Sizing rule variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
+the topk/n_drop SELECTION is identical to the reference, but the buy size is
+proportional to the score MAGNITUDE (edge) instead of equal-weight, capped at a
+fraction ``cap_frac`` of the equal-weight notional so a single name cannot
+over-concentrate the book.
+
+``cap_frac`` is the fraction of the equal-weight per-name notional that a top
+signal can deploy at most (e.g. 0.5 = at most half the equal-weight size).
+Names whose score is below the median of the buy set get a proportionally
+smaller slice; the residual stays in cash (that is the point of the rule:
+throw away less edge per name, deploy less capital when conviction is low).
+"""
+
+from __future__ import annotations
+
+from typing import List
+
+import numpy as np
+import pandas as pd
+
+from qlib.backtest import Order
+from qlib.backtest.decision import OrderDir, TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["FractionalKellyDropoutStrategy"]
+
+DEFAULT_CAP_FRAC = 0.5
+
+
+class FractionalKellyDropoutStrategy(TopkDropoutStrategy):
+    """TopkDropout selection with score-magnitude (fractional-Kelly) sizing.
+
+    Parameters
+    ----------
+    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
+    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
+    cap_frac : max buy notional as a fraction of the equal-weight notional.
+    """
+
+    def __init__(self, *, topk, n_drop, cap_frac: float = DEFAULT_CAP_FRAC, **kwargs):
+        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
+        self.cap_frac = cap_frac
+
+    def generate_trade_decision(self, execute_result=None):
+        import copy
+
+        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 isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+        if pred_score is None:
+            return TradeDecisionWO([], self)
+
+        if self.only_tradable:
+
+            def get_first_n(li, n, reverse=False):
+                cur_n = 0
+                res = []
+                for si in reversed(li) if reverse else li:
+                    if self.trade_exchange.is_stock_tradable(
+                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
+                    ):
+                        res.append(si)
+                        cur_n += 1
+                        if cur_n >= n:
+                            break
+                return res[::-1] if reverse else res
+
+            def get_last_n(li, n):
+                return get_first_n(li, n, reverse=True)
+
+            def filter_stock(li):
+                return [
+                    si
+                    for si in li
+                    if self.trade_exchange.is_stock_tradable(
+                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
+                    )
+                ]
+
+        else:
+
+            def get_first_n(li, n):
+                return list(li)[:n]
+
+            def get_last_n(li, n):
+                return list(li)[-n:]
+
+            def filter_stock(li):
+                return li
+
+        current_temp: "object" = copy.deepcopy(self.trade_position)
+        sell_order_list: List[Order] = []
+        buy_order_list: List[Order] = []
+        cash = current_temp.get_cash()
+        current_stock_list = current_temp.get_stock_list()
+        last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
+
+        if self.method_buy == "top":
+            today = get_first_n(
+                pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
+                self.n_drop + self.topk - len(last),
+            )
+        elif self.method_buy == "random":
+            topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
+            candi = list(filter(lambda x: x not in last, topk_candi))
+            n = self.n_drop + self.topk - len(last)
+            try:
+                today = np.random.choice(candi, n, replace=False)
+            except ValueError:
+                today = candi
+        else:
+            raise NotImplementedError(f"This type of input is not supported")
+
+        comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
+
+        if self.method_sell == "bottom":
+            sell = last[last.isin(get_last_n(comb, self.n_drop))]
+        elif self.method_sell == "random":
+            candi = filter_stock(last)
+            try:
+                sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
+            except ValueError:
+                sell = candi
+        else:
+            raise NotImplementedError(f"This type of input is not supported")
+
+        buy = today[: len(sell) + self.topk - len(last)]
+        for code in current_stock_list:
+            if not self.trade_exchange.is_stock_tradable(
+                stock_id=code,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
+            ):
+                continue
+            if code in sell:
+                time_per_step = self.trade_calendar.get_freq()
+                if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
+                    continue
+                sell_amount = current_temp.get_stock_amount(code=code)
+                sell_order = Order(
+                    stock_id=code,
+                    amount=sell_amount,
+                    start_time=trade_start_time,
+                    end_time=trade_end_time,
+                    direction=Order.SELL,
+                )
+                if self.trade_exchange.check_order(sell_order):
+                    sell_order_list.append(sell_order)
+                    trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
+                        sell_order, position=current_temp
+                    )
+                    cash += trade_val - trade_cost
+
+        if len(buy) == 0:
+            return TradeDecisionWO(sell_order_list, self)
+
+        # ---- fractional-Kelly sizing --------------------------------------
+        # equal-weight notional (reference baseline)
+        eq_notional = cash * self.risk_degree / len(buy)
+        buy_scores = pred_score.reindex(buy).astype(float)
+        lo, hi = buy_scores.min(), buy_scores.max()
+        if hi == lo:
+            w = pd.Series(1.0, index=buy_scores.index)
+        else:
+            w = (buy_scores - lo) / (hi - lo)  # [0,1] edge magnitude
+            w = w.clip(lower=0.0)
+            w_max = w.max()
+            w = w / w_max if w_max > 0 else w  # max == 1.0
+        for code in buy:
+            if not self.trade_exchange.is_stock_tradable(
+                stock_id=code,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
+            ):
+                continue
+            buy_price = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
+            )
+            notional = eq_notional * min(self.cap_frac, float(w.get(code, 0.0)))
+            buy_amount = notional / buy_price
+            factor = self.trade_exchange.get_factor(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
+            )
+            buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
+            buy_order = Order(
+                stock_id=code,
+                amount=buy_amount,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=Order.BUY,
+            )
+            buy_order_list.append(buy_order)
+
+        return TradeDecisionWO(sell_order_list + buy_order_list, self)

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

@@ -0,0 +1,231 @@
+"""HMM-regime overlay TopkDropout strategy.
+
+Regime-gate overlay on ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
+selection and sizing are identical to the reference, but a name is only BOUGHT
+(entry gate) when its per-symbol HMM regime posterior ``sp_hmm_p_regime1`` on
+the signal date is >= ``regime_threshold``; otherwise it is held in cash instead
+of being opened.
+
+The regime posterior is read from the lake feature provider on the fly via
+``qlib.data.D.features`` (field ``$sp_hmm_p_regime1``) for the signal window, so
+no regime column needs to enter the model's ``feature_fields`` — the gate is a
+pure overlay (book ch.01: regime flags regressed as model features, survived
+only as an overlay). The HMM itself was fit with ``fit_end=<train end>`` when
+the lake features were backfilled, so there is no lookahead.
+
+Names already held are NOT force-sold when the regime turns unfavourable
+(entry gate only, matching the queue-10 design).
+"""
+
+from __future__ import annotations
+
+from typing import List
+
+import numpy as np
+import pandas as pd
+
+from qlib.backtest import Order
+from qlib.backtest.decision import OrderDir, TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+try:
+    from qlib.data import D
+except ImportError:  # pragma: no cover - qlib always present in this stack
+    D = None
+
+__all__ = ["RegimeGateDropoutStrategy"]
+
+DEFAULT_REGIME_THRESHOLD = 0.5
+REGIME_FIELD = "$sp_hmm_p_regime1"
+
+
+class RegimeGateDropoutStrategy(TopkDropoutStrategy):
+    """TopkDropout with an HMM-regime entry gate on buy candidates.
+
+    Parameters
+    ----------
+    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
+    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
+    regime_threshold : minimum ``sp_hmm_p_regime1`` posterior required to open a
+        new position (default 0.5).
+    """
+
+    def __init__(self, *, topk, n_drop, regime_threshold: float = DEFAULT_REGIME_THRESHOLD, **kwargs):
+        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
+        self.regime_threshold = regime_threshold
+
+    def _regime_for(self, codes, pred_start, pred_end) -> pd.Series:
+        """Return {code: sp_hmm_p_regime1} for the signal window (last day)."""
+        if D is None:
+            return pd.Series(dtype=float)
+        try:
+            df = D.features(list(codes), [REGIME_FIELD], start_time=pred_start, end_time=pred_end, freq="day")
+        except Exception:  # noqa: BLE001 - a regime read failure should gate open, not crash
+            return pd.Series(dtype=float)
+        if df is None or len(df) == 0:
+            return pd.Series(dtype=float)
+        # df index is MultiIndex (datetime, instrument); take the last day's values
+        df = df.reset_index()
+        ts_col = "datetime" if "datetime" in df.columns else df.columns[0]
+        sym_col = "instrument" if "instrument" in df.columns else df.columns[1]
+        last_ts = df[ts_col].max()
+        last = df[df[ts_col] == last_ts]
+        out = {}
+        for _, row in last.iterrows():
+            sym = str(row[sym_col]).split("/")[-1].upper()
+            val = row.iloc[-1]
+            out[sym] = float(val) if val == val else np.nan
+        return pd.Series(out)
+
+    def generate_trade_decision(self, execute_result=None):
+        import copy
+
+        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 isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+        if pred_score is None:
+            return TradeDecisionWO([], self)
+
+        if self.only_tradable:
+
+            def get_first_n(li, n, reverse=False):
+                cur_n = 0
+                res = []
+                for si in reversed(li) if reverse else li:
+                    if self.trade_exchange.is_stock_tradable(
+                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
+                    ):
+                        res.append(si)
+                        cur_n += 1
+                        if cur_n >= n:
+                            break
+                return res[::-1] if reverse else res
+
+            def get_last_n(li, n):
+                return get_first_n(li, n, reverse=True)
+
+            def filter_stock(li):
+                return [
+                    si
+                    for si in li
+                    if self.trade_exchange.is_stock_tradable(
+                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
+                    )
+                ]
+
+        else:
+
+            def get_first_n(li, n):
+                return list(li)[:n]
+
+            def get_last_n(li, n):
+                return list(li)[-n:]
+
+            def filter_stock(li):
+                return li
+
+        current_temp: "object" = copy.deepcopy(self.trade_position)
+        sell_order_list: List[Order] = []
+        buy_order_list: List[Order] = []
+        cash = current_temp.get_cash()
+        current_stock_list = current_temp.get_stock_list()
+        last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
+
+        if self.method_buy == "top":
+            today = get_first_n(
+                pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
+                self.n_drop + self.topk - len(last),
+            )
+        elif self.method_buy == "random":
+            topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
+            candi = list(filter(lambda x: x not in last, topk_candi))
+            n = self.n_drop + self.topk - len(last)
+            try:
+                today = np.random.choice(candi, n, replace=False)
+            except ValueError:
+                today = candi
+        else:
+            raise NotImplementedError(f"This type of input is not supported")
+
+        comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
+
+        if self.method_sell == "bottom":
+            sell = last[last.isin(get_last_n(comb, self.n_drop))]
+        elif self.method_sell == "random":
+            candi = filter_stock(last)
+            try:
+                sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
+            except ValueError:
+                sell = candi
+        else:
+            raise NotImplementedError(f"This type of input is not supported")
+
+        buy = today[: len(sell) + self.topk - len(last)]
+
+        # ---- regime gate -----------------------------------------------------
+        if buy:
+            regime = self._regime_for(buy, pred_start_time, pred_end_time)
+            gated = [c for c in buy if regime.get(c, np.nan) >= self.regime_threshold]
+        else:
+            gated = []
+
+        for code in current_stock_list:
+            if not self.trade_exchange.is_stock_tradable(
+                stock_id=code,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
+            ):
+                continue
+            if code in sell:
+                time_per_step = self.trade_calendar.get_freq()
+                if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
+                    continue
+                sell_amount = current_temp.get_stock_amount(code=code)
+                sell_order = Order(
+                    stock_id=code,
+                    amount=sell_amount,
+                    start_time=trade_start_time,
+                    end_time=trade_end_time,
+                    direction=Order.SELL,
+                )
+                if self.trade_exchange.check_order(sell_order):
+                    sell_order_list.append(sell_order)
+                    trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
+                        sell_order, position=current_temp
+                    )
+                    cash += trade_val - trade_cost
+
+        if len(gated) == 0:
+            return TradeDecisionWO(sell_order_list, self)
+
+        value = cash * self.risk_degree / len(gated)
+        for code in gated:
+            if not self.trade_exchange.is_stock_tradable(
+                stock_id=code,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
+            ):
+                continue
+            buy_price = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
+            )
+            buy_amount = value / buy_price
+            factor = self.trade_exchange.get_factor(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
+            )
+            buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
+            buy_order = Order(
+                stock_id=code,
+                amount=buy_amount,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=Order.BUY,
+            )
+            buy_order_list.append(buy_order)
+
+        return TradeDecisionWO(sell_order_list + buy_order_list, self)

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

@@ -0,0 +1,169 @@
+"""Market-neutral top/bottom long-short strategy for cross-sectional signals.
+
+Captures the cross-sectional long-short spread net of costs: buys the top-ranked
+``topk`` names and shorts the bottom-ranked ``topk`` names, equal-weight per
+side, sized to ``risk_degree`` of total value per side. Rebalances daily to the
+current rank (dropout-free: the book converges to the latest top/bottom sets).
+
+The long and short legs use equal notional per side (gross exposure ~2x
+``risk_degree`` of NAV, i.e. approximately market neutral before transaction
+costs). Benchmark neutrality (SPY beta ~ 0) is the secondary sanity metric.
+"""
+
+from __future__ import annotations
+
+from typing import List
+
+import copy
+
+import pandas as pd
+
+from qlib.backtest import Order
+from qlib.backtest.decision import OrderDir, TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import BaseSignalStrategy
+
+__all__ = ["TopBottomDropoutStrategy"]
+
+DEFAULT_SHORT_LEG = True
+DEFAULT_REBALANCE_DAILY = True
+
+
+class TopBottomDropoutStrategy(BaseSignalStrategy):
+    """Long top-k / short bottom-k equal-weight market-neutral book.
+
+    Parameters
+    ----------
+    topk : number of names on each side (long top-k and short bottom-k).
+    short_leg : whether to open the short side (if False, long-only topk).
+    rebalance_daily : if True rebalance to current rank every day; else keep
+        positions and only refresh on score changes (dropout-style).
+    risk_degree : fraction of total value deployed per side.
+    """
+
+    def __init__(
+        self,
+        *,
+        topk: int = 10,
+        short_leg: bool = DEFAULT_SHORT_LEG,
+        rebalance_daily: bool = DEFAULT_REBALANCE_DAILY,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.topk = topk
+        self.short_leg = short_leg
+        self.rebalance_daily = rebalance_daily
+        self._prev_longs = set()
+        self._prev_shorts = set()
+
+    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 isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+        if pred_score is None or len(pred_score) == 0:
+            return TradeDecisionWO([], self)
+
+        # rank all names; topk longs and topk shorts
+        ranked = pred_score.sort_values(ascending=False)
+        longs = list(ranked.index[: self.topk])
+        shorts = list(ranked.index[-self.topk :]) if self.short_leg else []
+
+        current_temp: "object" = copy.deepcopy(self.trade_position)
+        current_codes = set(current_temp.get_stock_list())
+        holdings = {c: current_temp for c in current_codes if abs(current_temp.get_stock_amount(c)) > 1e-6}
+
+        sell_orders: List[Order] = []
+        buy_orders: List[Order] = []
+
+        def _tradable(code, direction):
+            try:
+                return self.trade_exchange.is_stock_tradable(
+                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=direction
+                )
+            except TypeError:
+                return self.trade_exchange.is_stock_tradable(
+                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time
+                )
+
+        # determine target set (long/short)
+        target_longs = set(longs)
+        target_shorts = set(shorts)
+
+        # close positions not in the target book
+        for code in list(holdings):
+            if code in target_longs or code in target_shorts:
+                continue
+            amt = abs(current_temp.get_stock_amount(code))
+            o = Order(
+                stock_id=code,
+                amount=amt,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=Order.SELL if code in target_longs else Order.SELL,
+            )
+            if self.trade_exchange.check_order(o):
+                sell_orders.append(o)
+                self.trade_exchange.deal_order(o, position=current_temp)
+
+        # equal-weight notional per side
+        total_value = current_temp.get_cash()
+        for code, pos in holdings.items():
+            if code in target_longs or code in target_shorts:
+                mark = self.trade_exchange.get_deal_price(
+                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.SELL
+                )
+                if mark is not None and mark == mark:
+                    total_value += abs(current_temp.get_stock_amount(code)) * mark
+
+        side_notional = total_value * self.risk_degree / max(1, self.topk)
+
+        for code in longs:
+            if code in holdings and abs(current_temp.get_stock_amount(code)) > 1e-6:
+                continue
+            px = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.BUY
+            )
+            if px is None or px != px or px <= 0:
+                continue
+            amount = side_notional / px
+            factor = self.trade_exchange.get_factor(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
+            )
+            amount = self.trade_exchange.round_amount_by_trade_unit(amount, factor)
+            o = Order(
+                stock_id=code,
+                amount=amount,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=Order.BUY,
+            )
+            if self.trade_exchange.check_order(o):
+                buy_orders.append(o)
+
+        if self.short_leg:
+            for code in shorts:
+                if code in holdings and abs(current_temp.get_stock_amount(code)) > 1e-6:
+                    continue
+                px = self.trade_exchange.get_deal_price(
+                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=Order.SELL
+                )
+                if px is None or px != px or px <= 0:
+                    continue
+                amount = side_notional / px
+                factor = self.trade_exchange.get_factor(
+                    stock_id=code, start_time=trade_start_time, end_time=trade_end_time
+                )
+                amount = self.trade_exchange.round_amount_by_trade_unit(amount, factor)
+                o = Order(
+                    stock_id=code,
+                    amount=amount,
+                    start_time=trade_start_time,
+                    end_time=trade_end_time,
+                    direction=Order.SELL,
+                )
+                if self.trade_exchange.check_order(o):
+                    sell_orders.append(o)
+
+        return TradeDecisionWO(sell_orders + buy_orders, self)

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

@@ -0,0 +1,202 @@
+"""Weekly-rebalance TopkDropout strategy.
+
+Turnover-reduction variant of ``qlib.contrib.strategy.signal_strategy.TopkDropoutStrategy``:
+the topk/n_drop selection and sizing are identical to the reference, but the
+target book is recomputed only on the first trading day of each ISO week; on the
+other days the strategy issues NO orders (holds the book untouched).
+
+The weekly cadence is derived from the qlib trade calendar: a rebalance happens
+when the current trade step's date belongs to a different ISO ``(year, week)``
+than the previous trade step. ``hold_band_pct`` (default 0) optionally skips
+tiny rebalances: when a name's existing position differs from the new target by
+less than this fraction, no order is generated for it.
+"""
+
+from __future__ import annotations
+
+from typing import List
+
+import numpy as np
+import pandas as pd
+
+from qlib.backtest import Order
+from qlib.backtest.decision import OrderDir, TradeDecisionWO
+from qlib.contrib.strategy.signal_strategy import TopkDropoutStrategy
+
+__all__ = ["WeeklyRebalanceDropoutStrategy"]
+
+DEFAULT_HOLD_BAND_PCT = 0.0
+
+
+class WeeklyRebalanceDropoutStrategy(TopkDropoutStrategy):
+    """TopkDropout rebalanced once per ISO week; holds otherwise.
+
+    Parameters
+    ----------
+    topk, n_drop, method_sell, method_buy, hold_thresh, only_tradable,
+    forbid_all_trade_at_limit : same as ``TopkDropoutStrategy``.
+    hold_band_pct : skip order for a name whose deviation from target weight is
+        below this fraction of the target (no-trade buffer band).
+    """
+
+    def __init__(self, *, topk, n_drop, hold_band_pct: float = DEFAULT_HOLD_BAND_PCT, **kwargs):
+        super().__init__(topk=topk, n_drop=n_drop, **kwargs)
+        self.hold_band_pct = hold_band_pct
+
+    @staticmethod
+    def _iso_week(ts) -> tuple:
+        return (ts.year, ts.week)
+
+    def generate_trade_decision(self, execute_result=None):
+        import copy
+
+        trade_step = self.trade_calendar.get_trade_step()
+        trade_start_time, trade_end_time = self.trade_calendar.get_step_time(trade_step)
+
+        cur_week = self._iso_week(trade_start_time)
+        prev_week = getattr(self, "_last_week", None)
+        self._last_week = cur_week
+
+        if prev_week is not None and prev_week == cur_week:
+            # not the first trading day of this ISO week -> hold
+            return TradeDecisionWO([], self)
+
+        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 isinstance(pred_score, pd.DataFrame):
+            pred_score = pred_score.iloc[:, 0]
+        if pred_score is None:
+            return TradeDecisionWO([], self)
+
+        if self.only_tradable:
+
+            def get_first_n(li, n, reverse=False):
+                cur_n = 0
+                res = []
+                for si in reversed(li) if reverse else li:
+                    if self.trade_exchange.is_stock_tradable(
+                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
+                    ):
+                        res.append(si)
+                        cur_n += 1
+                        if cur_n >= n:
+                            break
+                return res[::-1] if reverse else res
+
+            def get_last_n(li, n):
+                return get_first_n(li, n, reverse=True)
+
+            def filter_stock(li):
+                return [
+                    si
+                    for si in li
+                    if self.trade_exchange.is_stock_tradable(
+                        stock_id=si, start_time=trade_start_time, end_time=trade_end_time
+                    )
+                ]
+
+        else:
+
+            def get_first_n(li, n):
+                return list(li)[:n]
+
+            def get_last_n(li, n):
+                return list(li)[-n:]
+
+            def filter_stock(li):
+                return li
+
+        current_temp: "object" = copy.deepcopy(self.trade_position)
+        sell_order_list: List[Order] = []
+        buy_order_list: List[Order] = []
+        cash = current_temp.get_cash()
+        current_stock_list = current_temp.get_stock_list()
+        last = pred_score.reindex(current_stock_list).sort_values(ascending=False).index
+
+        if self.method_buy == "top":
+            today = get_first_n(
+                pred_score[~pred_score.index.isin(last)].sort_values(ascending=False).index,
+                self.n_drop + self.topk - len(last),
+            )
+        elif self.method_buy == "random":
+            topk_candi = get_first_n(pred_score.sort_values(ascending=False).index, self.topk)
+            candi = list(filter(lambda x: x not in last, topk_candi))
+            n = self.n_drop + self.topk - len(last)
+            try:
+                today = np.random.choice(candi, n, replace=False)
+            except ValueError:
+                today = candi
+        else:
+            raise NotImplementedError(f"This type of input is not supported")
+
+        comb = pred_score.reindex(last.union(pd.Index(today))).sort_values(ascending=False).index
+
+        if self.method_sell == "bottom":
+            sell = last[last.isin(get_last_n(comb, self.n_drop))]
+        elif self.method_sell == "random":
+            candi = filter_stock(last)
+            try:
+                sell = pd.Index(np.random.choice(candi, self.n_drop, replace=False) if len(last) else [])
+            except ValueError:
+                sell = candi
+        else:
+            raise NotImplementedError(f"This type of input is not supported")
+
+        buy = today[: len(sell) + self.topk - len(last)]
+        for code in current_stock_list:
+            if not self.trade_exchange.is_stock_tradable(
+                stock_id=code,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=None if self.forbid_all_trade_at_limit else OrderDir.SELL,
+            ):
+                continue
+            if code in sell:
+                time_per_step = self.trade_calendar.get_freq()
+                if current_temp.get_stock_count(code, bar=time_per_step) < self.hold_thresh:
+                    continue
+                sell_amount = current_temp.get_stock_amount(code=code)
+                sell_order = Order(
+                    stock_id=code,
+                    amount=sell_amount,
+                    start_time=trade_start_time,
+                    end_time=trade_end_time,
+                    direction=Order.SELL,
+                )
+                if self.trade_exchange.check_order(sell_order):
+                    sell_order_list.append(sell_order)
+                    trade_val, trade_cost, trade_price = self.trade_exchange.deal_order(
+                        sell_order, position=current_temp
+                    )
+                    cash += trade_val - trade_cost
+
+        if len(buy) == 0:
+            return TradeDecisionWO(sell_order_list, self)
+
+        value = cash * self.risk_degree / len(buy)
+        for code in buy:
+            if not self.trade_exchange.is_stock_tradable(
+                stock_id=code,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=None if self.forbid_all_trade_at_limit else OrderDir.BUY,
+            ):
+                continue
+            buy_price = self.trade_exchange.get_deal_price(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time, direction=OrderDir.BUY
+            )
+            buy_amount = value / buy_price
+            factor = self.trade_exchange.get_factor(
+                stock_id=code, start_time=trade_start_time, end_time=trade_end_time
+            )
+            buy_amount = self.trade_exchange.round_amount_by_trade_unit(buy_amount, factor)
+            buy_order = Order(
+                stock_id=code,
+                amount=buy_amount,
+                start_time=trade_start_time,
+                end_time=trade_end_time,
+                direction=Order.BUY,
+            )
+            buy_order_list.append(buy_order)
+
+        return TradeDecisionWO(sell_order_list + buy_order_list, self)

queue/README.md

@@ -0,0 +1,69 @@
+# 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

@@ -0,0 +1,26 @@
+# 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

@@ -0,0 +1,22 @@
+# 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

@@ -1,4 +1,12 @@
-# Exact compact stochastic feature set requested for a new run in MLflow exp 25.
+# 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" %}
@@ -20,7 +28,7 @@ qlib_init:
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q12-label22d-weekly" }
 
 task:
     model:
@@ -58,7 +66,7 @@ task:
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
-                    label: "Ref($close,-6)/Ref($close,-1)-1"
+                    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" } }
@@ -79,9 +87,9 @@ task:
           kwargs:
               config:
                   strategy:
-                      class: TopkDropoutStrategy
+                      class: WeeklyRebalanceDropoutStrategy
-                      module_path: qlib.contrib.strategy
+                      module_path: tac_qlib.contrib.strategy.weekly_rebalance
-                      kwargs: { signal: "<PRED>", topk: 10, n_drop: 2, only_tradable: true, risk_degree: 0.95 }
+                      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

queue/workflows/q13_weekly_second_window.yaml

@@ -0,0 +1,106 @@
+# 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

@@ -0,0 +1,107 @@
+# 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

queue/workflows/q15_single_seed.yaml

@@ -1,9 +1,14 @@
-# M3 isolation run: base compact set + GARCH(1,1) vol-regime trio.
+# QUEUE-15 — 5-seed vs single-model clean A/B on the compact stochastic set.
-# Exact copy of exp26 (reference: expId=25 run=21afc6afdb674a399b59dd76c97628ce)
+# CLAIMS.md HYPOTHESIS: "5-seed RankIC ensemble raises performance vs single model
-# except feature_fields. 5-seed ensemble.
+# 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
 {%- 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_garch_cond_var,sp_garch_persistence,sp_garch_std_resid" %}
+{%- 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 }}"
@@ -22,7 +27,7 @@ qlib_init:
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp31-m3-garch" }
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q15-single-seed" }
 
 task:
     model:
@@ -42,7 +47,7 @@ task:
             subsample_freq: 1
             reg_alpha: 0.1
             reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
+            seeds: "2026"
 
     dataset:
         class: DatasetH

queue/workflows/q16_hmm_features.yaml

@@ -1,9 +1,15 @@
-# M2 isolation run: base compact set + risk-adjusted drift sp_sharpe_22.
+# QUEUE-16 — HMM family added as model features to the compact set.
-# Exact copy of exp26 (reference: expId=25 run=21afc6afdb674a399b59dd76c97628ce)
+# CLAIMS.md HYPOTHESIS: "Dropping model-specific feature families (ou, hmm)
-# except feature_fields. 5-seed ensemble.
+# 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
 {%- 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_sharpe_22" %}
+{%- 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" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
@@ -22,7 +28,7 @@ qlib_init:
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp30-m2-sharpe" }
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q16-hmm-features" }
 
 task:
     model:

queue/workflows/q17_moments_features.yaml

@@ -1,8 +1,15 @@
-# Compact stochastic feature set with reduced turnover: n_drop=1 instead of 2.
+# QUEUE-17 — Realized-moments family added to the compact set.
-# Same setup as exp24 (compact baseline) but replacing the TopkDropout n_drop 2 with 1.
+# 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
 {%- 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 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" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
@@ -21,7 +28,7 @@ qlib_init:
     exp_manager:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
-        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-exp22-stochastic-general" }
+        kwargs: { uri: "sqlite:///mlruns.db", default_exp_name: "tac-rd-q17-moments-features" }
 
 task:
     model:

queue/workflows/q18_optstop.yaml

@@ -0,0 +1,106 @@
+# 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
+{%- 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-q18-optstop" }
+
+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: 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 }
+                  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

@@ -1,133 +0,0 @@
-# -----------------------------------------------------------------------------
-# 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

@@ -1,134 +0,0 @@
-# -----------------------------------------------------------------------------
-# 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

@@ -1,141 +0,0 @@
-# -----------------------------------------------------------------------------
-# 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/exp22/workflow.yaml

@@ -1,97 +0,0 @@
-# Re-run of experiment 16 with validated family=ta and family=sp lake features.
-{%- 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,sma_5,sma_20,ema_12,ema_26,rsi_14,macd,macd_signal,macd_hist,bb_upper,bb_middle,bb_lower,atr_14,adx_14,sp_ret,sp_ou_half_life,sp_ou_revert,sp_ou_zscore,sp_hmm_p_regime1,sp_hmm_state,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_down,sp_max_move,sp_max_up,sp_rv1,sp_rv5,sp_rv22,sp_rv_ac1,sp_rv_cv_22,sp_vol_ratio_1_22,sp_vol_ratio_5_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_1,sp_dsv_5,sp_dsv_22,sp_dsv_ratio_1,sp_dsv_ratio_5,sp_dsv_ratio_22,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_sig_level2_lead_lag_5,sp_sig_level2_lag_lead_5" %}
-
-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-exp16-db-ta-sp" }
-
-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: 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/exp23/workflow.yaml

@@ -1,97 +0,0 @@
-# General stochastic-process feature ablation: no TA, HMM, or OU fields.
-{%- 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_down,sp_max_move,sp_max_up,sp_rv1,sp_rv5,sp_rv22,sp_rv_ac1,sp_rv_cv_22,sp_vol_ratio_1_22,sp_vol_ratio_5_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_rskew_5,sp_rskew_22,sp_rkurt_5,sp_rkurt_22,sp_dsv_1,sp_dsv_5,sp_dsv_22,sp_dsv_ratio_1,sp_dsv_ratio_5,sp_dsv_ratio_22,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead,sp_sig_level2_lead_lag_5,sp_sig_level2_lag_lead_5" %}
-
-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-exp22-stochastic-general" }
-
-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: 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