add q08 risk-limit calibration evidence (A/B results)

code/MANIFEST.txt

@@ -1,5 +1,5 @@
 # TradeAC custom-qlib-code snapshot (auto-generated)
-# parent repo HEAD : 59839ff48760b632a2d1bb40877766b1da105891
+# parent repo HEAD : 507846cee16eeee11daf33c4176e8aec79b985b2
 #   tac-qlib/tac_qlib/contrib
 #   tac-qlib/tac_qlib/data
 # per-file hashes (git hash-object):

evidence/q08-risklimit/RESULT.md

@@ -0,0 +1,35 @@
+# Q08 — Risk-limit A/B re-validation (trace 40)
+
+**Status:** DONE (verdict: REFUTED as an IR edge; safety-net value retained)
+
+## Input
+- Reference signal: exp-26 pred, run `21afc6afdb674a399b59dd76c97628ce` (mlflow exp 25)
+- Window: 2026-01-04 → 2026-08-10, Topk10 n_drop1, SPY benchmark, $1M, 5/15bp/$5
+- Tool: `rd_risk_calibrate` (A/B + sensitivity grid). Full JSON: `risk_calibration.json`
+
+## Candidate spec (round-3 live spec)
+`{"liquidity_floor_adv": 5000000, "size_cap_pct": 0.12, "concentration_cap_pct": 0.95, "drawdown_pause_pct": 0.10}`
+
+## Results (net, with cost)
+| Config | IR | Ann. return | Max DD |
+|---|---|---|---|
+| baseline (no limits) | 1.5804 | +27.50% | −6.91% |
+| **candidate (5M floor + caps)** | **1.5121** | +2.20% | **−0.65%** |
+| liquidity $10M | 1.5457 | +2.25% | −0.64% |
+
+## Findings
+- **Floor binds, not a no-op**: $5M liquidity floor dropped 8 symbols —
+  `DBA, DBC, ESPO, FDN, REM, TAN, UNG, XAR`.
+- **No IR edge from the gate**: candidate IR (1.512) is BELOW baseline (1.580).
+  The exp-18 direction (floor IR 0.81→0.98) does NOT reproduce on the clean-lake
+  reference signal.
+- **Drawdown cut is pure defunding**: size_cap 0.12 × concentration 0.95 fold
+  the effective risk_degree to ~0.0095 → ~$9.5k deployed of $1M (~100x less).
+  Sensitivity grid shows both caps are no-ops (conc 20–50% identical,
+  size_cap 5–20% identical); only the liquidity floor moves returns, marginally.
+- **Conclusion**: keep the live spec as a safety net; there is no risk-limit
+  gate IR edge to harvest when the signal is the bottleneck (exp-20 pattern).
+
+## Artifacts on this branch
+- `evidence/q08-risklimit/risk_calibration.json` — full calibration dump
+- `queue/designs/q08_risk_limit_ab.md` — the pre-registered design doc

evidence/q08-risklimit/risk_calibration.json

@@ -0,0 +1,401 @@
+{
+  "rows": [
+    {
+      "label": "baseline (no limits)",
+      "mean": 0.001155,
+      "std": 0.011279,
+      "annualized_return": 0.274989,
+      "information_ratio": 1.580427,
+      "max_drawdown": -0.069145
+    },
+    {
+      "label": "liquidity $10,000,000",
+      "mean": 9.4e-05,
+      "std": 0.000942,
+      "annualized_return": 0.022464,
+      "information_ratio": 1.545736,
+      "max_drawdown": -0.006389
+    },
+    {
+      "label": "conc 20%",
+      "mean": 0.000115,
+      "std": 0.001168,
+      "annualized_return": 0.027285,
+      "information_ratio": 1.513718,
+      "max_drawdown": -0.008104
+    },
+    {
+      "label": "conc 30%",
+      "mean": 0.000115,
+      "std": 0.001168,
+      "annualized_return": 0.027285,
+      "information_ratio": 1.513718,
+      "max_drawdown": -0.008104
+    },
+    {
+      "label": "conc 40%",
+      "mean": 0.000115,
+      "std": 0.001168,
+      "annualized_return": 0.027285,
+      "information_ratio": 1.513718,
+      "max_drawdown": -0.008104
+    },
+    {
+      "label": "conc 50%",
+      "mean": 0.000115,
+      "std": 0.001168,
+      "annualized_return": 0.027285,
+      "information_ratio": 1.513718,
+      "max_drawdown": -0.008104
+    },
+    {
+      "label": "candidate {\"liquidity_floor_adv\": 5000000.0, \"size_cap_pct\": 0.12, \"concentration_cap_pct\": 0.95, \"drawdown_pause_pct\": 0.1}",
+      "mean": 9.2e-05,
+      "std": 0.000943,
+      "annualized_return": 0.021991,
+      "information_ratio": 1.512051,
+      "max_drawdown": -0.00653
+    },
+    {
+      "label": "size_cap 5%",
+      "mean": 9.2e-05,
+      "std": 0.000943,
+      "annualized_return": 0.021991,
+      "information_ratio": 1.512051,
+      "max_drawdown": -0.00653
+    },
+    {
+      "label": "size_cap 10%",
+      "mean": 9.2e-05,
+      "std": 0.000943,
+      "annualized_return": 0.021991,
+      "information_ratio": 1.512051,
+      "max_drawdown": -0.00653
+    },
+    {
+      "label": "size_cap 15%",
+      "mean": 9.2e-05,
+      "std": 0.000943,
+      "annualized_return": 0.021991,
+      "information_ratio": 1.512051,
+      "max_drawdown": -0.00653
+    },
+    {
+      "label": "size_cap 20%",
+      "mean": 9.2e-05,
+      "std": 0.000943,
+      "annualized_return": 0.021991,
+      "information_ratio": 1.512051,
+      "max_drawdown": -0.00653
+    },
+    {
+      "label": "liquidity $5,000,000",
+      "mean": 9.2e-05,
+      "std": 0.000943,
+      "annualized_return": 0.021991,
+      "information_ratio": 1.512051,
+      "max_drawdown": -0.00653
+    },
+    {
+      "label": "liquidity $1,000,000",
+      "mean": 9.1e-05,
+      "std": 0.000929,
+      "annualized_return": 0.021625,
+      "information_ratio": 1.508748,
+      "max_drawdown": -0.006376
+    },
+    {
+      "label": "liquidity $2,500,000",
+      "mean": 7.1e-05,
+      "std": 0.000918,
+      "annualized_return": 0.017,
+      "information_ratio": 1.199721,
+      "max_drawdown": -0.007158
+    }
+  ],
+  "runs": {
+    "baseline": {
+      "risk": {
+        "mean": 0.0011554172081987572,
+        "std": 0.01127853762493476,
+        "annualized_return": 0.27498929555130425,
+        "information_ratio": 1.5804272791471323,
+        "max_drawdown": -0.06914515336341577
+      },
+      "applied": {}
+    },
+    "candidate": {
+      "risk": {
+        "mean": 9.239707947451976e-05,
+        "std": 0.0009427144352738658,
+        "annualized_return": 0.0219905049149357,
+        "information_ratio": 1.5120514373488407,
+        "max_drawdown": -0.006530482262119444
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "size_cap 5%": {
+      "risk": {
+        "mean": 9.239707947451976e-05,
+        "std": 0.0009427144352738658,
+        "annualized_return": 0.0219905049149357,
+        "information_ratio": 1.5120514373488407,
+        "max_drawdown": -0.006530482262119444
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "size_cap 10%": {
+      "risk": {
+        "mean": 9.239707947451976e-05,
+        "std": 0.0009427144352738658,
+        "annualized_return": 0.0219905049149357,
+        "information_ratio": 1.5120514373488407,
+        "max_drawdown": -0.006530482262119444
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "size_cap 15%": {
+      "risk": {
+        "mean": 9.239707947451976e-05,
+        "std": 0.0009427144352738658,
+        "annualized_return": 0.0219905049149357,
+        "information_ratio": 1.5120514373488407,
+        "max_drawdown": -0.006530482262119444
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "size_cap 20%": {
+      "risk": {
+        "mean": 9.239707947451976e-05,
+        "std": 0.0009427144352738658,
+        "annualized_return": 0.0219905049149357,
+        "information_ratio": 1.5120514373488407,
+        "max_drawdown": -0.006530482262119444
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "conc 20%": {
+      "risk": {
+        "mean": 0.00011464156491316718,
+        "std": 0.0011683839517000441,
+        "annualized_return": 0.027284692449333788,
+        "information_ratio": 1.5137180903503433,
+        "max_drawdown": -0.008103887185240407
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "conc 30%": {
+      "risk": {
+        "mean": 0.00011464156491316718,
+        "std": 0.0011683839517000441,
+        "annualized_return": 0.027284692449333788,
+        "information_ratio": 1.5137180903503433,
+        "max_drawdown": -0.008103887185240407
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "conc 40%": {
+      "risk": {
+        "mean": 0.00011464156491316718,
+        "std": 0.0011683839517000441,
+        "annualized_return": 0.027284692449333788,
+        "information_ratio": 1.5137180903503433,
+        "max_drawdown": -0.008103887185240407
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "conc 50%": {
+      "risk": {
+        "mean": 0.00011464156491316718,
+        "std": 0.0011683839517000441,
+        "annualized_return": 0.027284692449333788,
+        "information_ratio": 1.5137180903503433,
+        "max_drawdown": -0.008103887185240407
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "liquidity $1,000,000": {
+      "risk": {
+        "mean": 9.086210454881382e-05,
+        "std": 0.0009290831160004576,
+        "annualized_return": 0.021625180882617688,
+        "information_ratio": 1.508747982736451,
+        "max_drawdown": -0.006376134679664126
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "ESPO"
+        ]
+      }
+    },
+    "liquidity $2,500,000": {
+      "risk": {
+        "mean": 7.142665167642606e-05,
+        "std": 0.0009184775632266332,
+        "annualized_return": 0.016999543098989402,
+        "information_ratio": 1.1997208834083914,
+        "max_drawdown": -0.0071582979845040825
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "REM",
+          "XAR"
+        ]
+      }
+    },
+    "liquidity $5,000,000": {
+      "risk": {
+        "mean": 9.239707947451976e-05,
+        "std": 0.0009427144352738658,
+        "annualized_return": 0.0219905049149357,
+        "information_ratio": 1.5120514373488407,
+        "max_drawdown": -0.006530482262119444
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "REM",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    },
+    "liquidity $10,000,000": {
+      "risk": {
+        "mean": 9.438545151345752e-05,
+        "std": 0.0009420158170657147,
+        "annualized_return": 0.02246373746020289,
+        "information_ratio": 1.5457360696934006,
+        "max_drawdown": -0.006388809561209335
+      },
+      "applied": {
+        "dropped_liquidity": [
+          "DBA",
+          "DBC",
+          "ESPO",
+          "FDN",
+          "ICLN",
+          "ITA",
+          "MDY",
+          "REM",
+          "SHY",
+          "TAN",
+          "UNG",
+          "XAR"
+        ]
+      }
+    }
+  },
+  "candidate": {
+    "liquidity_floor_adv": 5000000.0,
+    "size_cap_pct": 0.12,
+    "concentration_cap_pct": 0.95,
+    "drawdown_pause_pct": 0.1
+  }
+}

queue/designs/q08_risk_limit_ab.md

@@ -0,0 +1,34 @@
+# QUEUE-08 — Risk-limit A/B re-validation: $5M liquidity floor on the exp-26 reference
+
+**Status:** QUEUED · **Priority:** P1 · **Effort:** tool-only (no new code)
+
+## Hypothesis (prove)
+The $5M liquidity floor improves net IR and cuts drawdown on the **post-reset**
+reference signal (pre-reset exp 18, EVIDENCE#008: net IR 0.81→0.98, cumDD
+7.93%→5.44%), while size/concentration caps hurt by cutting deployed capital.
+Needs re-validation on the exp-26 lineage because exp 18 is pre-clean-lake and
+not comparable (EVIDENCE#009/010). Source: `book/CLAIMS.md` open question +
+`book/README.md` `TODO(evidence-needed: reconciliation of exp 18 risk-limit spec
+on the post-reset reference signal)`.
+
+## Change vs exp-26 reference (ONE variable)
+- Reference: the saved exp-26 prediction (run `21afc6af…`, mlflow exp 25).
+- A/B via `rd_risk_calibrate` (runs limit-vs-no-limit A/B + sensitivity grid
+  over size_cap_pct, concentration_cap_pct, liquidity_floor_adv) and/or
+  `rd_backtest` with `risk_limits` on the SAME saved `pred.pkl`:
+  - baseline: no limits (this must reproduce the exp-26 net +2.13% / IR 0.21);
+  - candidate: `{"liquidity_floor_adv": 5000000, "size_cap_pct": 0.12,
+    "concentration_cap_pct": 0.95, "drawdown_pause_pct": 0.10}` (round-3 spec).
+- Pick the spec (B2 calibration) that keeps live ≈ backtest.
+
+## Acceptance
+- Candidate spec: `net_IR > 0.21` AND `net_max_drawdown < 7.69%` vs no-limit on
+  the same pred. Size/concentration caps expected to REDUCE deployed capital
+  (record the direction as confirmation of exp 18).
+- If the floor is a no-op (gates don't bind at this signal) → report that gates
+  are no-ops when the signal is the bottleneck (exp 20 pattern) as a PROVEN
+  clean-lake result.
+
+## Execution prerequisites
+- None (uses saved pred + `rd_risk_calibrate`/`rd_backtest`). Trace the A/B as
+  an experiment; record the spec chosen for the next live round.

workflows/ablate_baseline_all_sp_fields.yaml

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

workflows/ablate_generic_only_sp_fields.yaml

@@ -1,25 +1,17 @@
-# QUEUE-ly
+# -----------------------------------------------------------------------------
-# Weekly rebalance (Q07): TopkDropout recomputed once per ISO week, hold otherwise (turnover relief).
+# ABLATION B (generic-only): same panel/model as the baseline, but feature
-# Acceptance: total_cost/turnover strictly below reference AND net_IR > 0.21 AND net_ann > +2.13%.
+# 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 FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
@@ -49,12 +41,12 @@ qlib_init:
         module_path: qlib.workflow.expm
         kwargs:
             uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-q07-weekly"
+            default_exp_name: "tac-rd-rank-ablate"
 
 task:
     model:
-        class: RankICEnsembleLGBModel
+        class: RankICLGBModel
-        module_path: tac_qlib.contrib.model.rank_ensemble
+        module_path: tac_qlib.contrib.model.rank_gbdt
         kwargs:
             loss: mse
             learning_rate: 0.02
@@ -69,8 +61,7 @@ task:
             subsample_freq: 1
             reg_alpha: 0.1
             reg_lambda: 1.0
-            seeds: "42,7,2026,99,123"
+            seed: 42
-            parallel: 5
 
     dataset:
         class: DatasetH
@@ -83,13 +74,13 @@ task:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
                     end_time: 2026-08-10
-                    fit_start_time: 2016-01-04
+                    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: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                     infer_processors:
                         - class: DropAllNaN
                           kwargs: {}
@@ -102,7 +93,7 @@ task:
                         - class: Fillna
                           kwargs: {}
             segments:
-                train: [2016-01-04, 2025-09-01]
+                train: [2015-01-03, 2025-09-01]
                 valid: [2025-09-03, 2026-01-03]
                 test: [2026-01-04, 2026-08-10]
 
@@ -120,12 +111,12 @@ task:
           kwargs:
               config:
                   strategy:
-                      class: WeeklyRebalanceDropoutStrategy
+                      class: TopkDropoutStrategy
-                      module_path: tac_qlib.contrib.strategy.weekly_rebalance
+                      module_path: qlib.contrib.strategy
                       kwargs:
                           signal: "<PRED>"
                           topk: 10
-                          n_drop: 1
+                          n_drop: 2
                           only_tradable: true
                           risk_degree: 0.95
                   backtest:
@@ -140,4 +131,4 @@ task:
                           open_cost: 0.0005
                           close_cost: 0.0015
                           min_cost: 5.0
-              risk_analysis_freq: 1d
+              risk_analysis_freq: 1d

workflows/exp12_isolation_ensemble.yaml

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

workflows/exp18-risk-limit/a_baseline.yaml

@@ -1,22 +1,23 @@
 # -----------------------------------------------------------------------------
-# QUEUE-03 — topk 20 vs 10 diversification on the compact reference.
+# EXP 18 - Risk-limit control: reference model + TopkDropout baseline (A).
 #
-# Hypothesis (book ch.05/chat-ideas): the effective independent names in the
+# Signal/model identical to the reference (tac-rd-rank-ensemble-isolated,
-# 50-ETF book is small (~4, chat-derived eigenvalue analysis); raising topk
+# run 0cea66d9...): RankICEnsembleLGBModel (parallel, 5 seeds) on the 50-ETF
-# diversifies the book and should cut drawdown / raise net IR without hurting
+# SP-5d panel, test 2026-01-04..2026-08-10. This workflow reproduces the
-# the (weak) rank signal — cost relief by spreading the book wider.
+# unconstrained TopkDropout baseline net-of-cost so the risk-limited variant
+# (same pred, liquidity/size/concentration caps) can be compared 1:1.
 #
-# Change vs exp-26 reference: ONE variable — strategy topk 10 -> 20 (n_drop 1).
+# The risk_limits spec itself is applied via rd_backtest / rd_strategy_targets
-# Everything else identical.
+# (tool-level param, not a YAML key); this run records the unconstrained
+# baseline that the limit A/B is measured against.
 #
-# Acceptance: net_IR > 0.21 AND net_max_drawdown < 7.69% AND net_ann_return >=
+# Run:
-#   +2.13%; watch total_cost — more names held must not raise turnover/cost.
+#   rd_run_workflow config_path=experiments/workflows/exp18-risk-limit/a_baseline.yaml \
-# Run: rd_run_workflow config_path=<repo>/experiments/queue/workflows/q03_topk20.yaml \
+#       experiment_name=tac-rd-risk-limit
-#        experiment_name=tac-rd-q03-topk20
 # -----------------------------------------------------------------------------
 {%- set LAKE = TAC_LAKE_DIR %}
 {%- set UNIVERSE = "SPY,QQQ,DIA,IWM,MDY,VTI,VOO,VEA,VWO,VT,EFA,EEM,TLT,IEF,SHY,AGG,BND,LQD,HYG,JNK,EMB,GLD,SLV,USO,UNG,DBA,DBC,XLK,XLF,XLE,XLV,XLI,XLY,XLP,XLU,XLB,XLRE,ARKK,SMH,SOXX,IBB,XBI,ITA,XAR,ICLN,TAN,FDN,IGV,ESPO,REM" %}
-{%- set FEATURES = "$open,$high,$low,$close,$vwap,$volume,sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
+{%- set SP_FIELDS = "sp_ret,sp_jump_ratio,sp_jump_flag,sp_jump_tail,sp_max_move,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_trend_slope_5,sp_trend_slope_20,sp_trend_slope_60,sp_logp,sp_hurst_exponent,sp_sig_level1_lead,sp_sig_level1_lag,sp_sig_level2_lead_lag,sp_sig_level2_lag_lead" %}
 
 qlib_init:
     provider_uri: "{{ LAKE }}"
@@ -46,7 +47,7 @@ qlib_init:
         module_path: qlib.workflow.expm
         kwargs:
             uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-q03-topk20"
+            default_exp_name: "tac-rd-risk-limit"
 
 task:
     model:
@@ -79,14 +80,14 @@ task:
                 kwargs:
                     instruments: "{{ UNIVERSE }}"
                     start_time: 2015-01-03
-                    end_time: 2026-08-10
+                    end_time: 2026-08-14
                     fit_start_time: 2016-01-04
                     fit_end_time: 2025-09-01
                     freq: day
                     lake_root: "{{ LAKE }}"
                     market: US
                     label: "Ref($close,-6)/Ref($close,-1)-1"
-                    feature_fields: "{{ FEATURES }}"
+                    feature_fields: "$open,$high,$low,$close,$vwap,$volume,{{ SP_FIELDS }}"
                     infer_processors:
                         - class: DropAllNaN
                           kwargs: {}
@@ -121,8 +122,8 @@ task:
                       module_path: qlib.contrib.strategy
                       kwargs:
                           signal: "<PRED>"
-                          topk: 20
+                          topk: 10
-                          n_drop: 1
+                          n_drop: 2
                           only_tradable: true
                           risk_degree: 0.95
                   backtest:
@@ -137,4 +138,4 @@ task:
                           open_cost: 0.0005
                           close_cost: 0.0015
                           min_cost: 5.0
-              risk_analysis_freq: 1d
+              risk_analysis_freq: 1d