exp 14: enhanced stochastic-control allocation - workflow YAMLs (A: TopkDropout baseline, B: OptimalStopControlV2)

workflows/exp14-optstop-v2/a_topk_baseline.yaml

@@ -1,16 +1,15 @@
 # -----------------------------------------------------------------------------
-# OPTSTOP VARIANT of the isolation winner (exp 12 / mlflow exp 16).
+# EXP 14 - Strategy A (baseline): reference model + TopkDropout.
 #
-# Same signal pipeline as exp-12 exactly: ablate-B generic-only sp_* features
+# Model = RankICEnsembleLGBModel (5-seed RankIC-early-stopped LGB), the class
-# (jump,har,trend,hurst,signature) on full backfilled 2016+ history, 5-seed
+# wired by the tac-rd-rank-ensemble-isolated reference (run 0cea66d9...).
-# RankICEnsembleLGBModel (42,7,2026,99,123). ONLY the portfolio construction
+# Strategy = TopkDropout topk=10 n_drop=2 risk_degree=0.95 (the reference's own
-# changes: TopkDropout (topk=10 n_drop=2) -> OptimalStopControl stochastic
+# recorded backtest strategy), so this run reproduces the reference baseline on
-# control strategy (percentile-gated entry, optimal-stopping exits by
+# the same 50-ETF SP-5d panel.
-# percentile/time/stop-loss, equal-weight notional).
 #
 # Run:
-#   rd_run_workflow config_path=experiments/workflows/exp13_optstop_isolation.yaml \
+#   rd_run_workflow config_path=experiments/workflows/exp14-optstop-v2/a_topk_baseline.yaml \
-#       experiment_name=tac-rd-rank-ensemble-optstop
+#       experiment_name=tac-rd-optstop-v2
 # -----------------------------------------------------------------------------
 {%- 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" %}
@@ -43,8 +42,8 @@ qlib_init:
         class: MLflowExpManager
         module_path: qlib.workflow.expm
         kwargs:
-            uri: "sqlite:///mlruns.db"
+            uri: "sqlite:///{{ LAKE }}/mlruns.db"
-            default_exp_name: "tac-rd-rank-ensemble-optstop"
+            default_exp_name: "tac-rd-optstop-v2"
 
 task:
     model:
@@ -114,16 +113,13 @@ task:
           kwargs:
               config:
                   strategy:
-                      class: OptimalStopControl
+                      class: TopkDropoutStrategy
-                      module_path: tac_qlib.contrib.strategy.optimal_stop
+                      module_path: qlib.contrib.strategy
                       kwargs:
                           signal: "<PRED>"
                           topk: 10
-                          entry_pct: 0.85
+                          n_drop: 2
-                          exit_pct: 0.7
+                          only_tradable: true
-                          max_hold_days: 10
-                          min_hold_days: 2
-                          sl: -0.08
                           risk_degree: 0.95
                   backtest:
                       start_time: 2026-01-04

workflows/exp14-optstop-v2/b_optstop_v2.yaml

@@ -0,0 +1,149 @@
+# -----------------------------------------------------------------------------
+# EXP 14 - Strategy B (enhanced): reference model + OptimalStopControlV2.
+#
+# Model = RankICEnsembleLGBModel (5-seed RankIC-early-stopped LGB), identical to
+# Strategy A. Strategy = OptimalStopControlV2 (tac_qlib.contrib.strategy.
+# optimal_stop_v2) with the controls that address OptimalStopControl's documented
+# weaknesses:
+#   - turnover / cost control: rebalance_band=0.05 (skip small rebalances),
+#     cooldown_days=3 (no whipsaw re-entries), max_turnover=0.30 (cap daily
+#     traded notional, priority exits > opens > rebalances)
+#   - robust thresholds (no valid-window overfit): entry 0.85 / exit 0.70 /
+#     max_hold 10 / min_hold 2 / sl -0.08
+# Sizing = equal-weight control (risk_degree fraction of total value split
+# across targets) - the "proper allocation" that replaces cash-heuristic sizing.
+#
+# Run:
+#   rd_run_workflow config_path=experiments/workflows/exp14-optstop-v2/b_optstop_v2.yaml \
+#       experiment_name=tac-rd-optstop-v2
+# -----------------------------------------------------------------------------
+{%- 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-optstop-v2"
+
+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: OptimalStopControlV2
+                      module_path: tac_qlib.contrib.strategy.optimal_stop_v2
+                      kwargs:
+                          signal: "<PRED>"
+                          topk: 10
+                          entry_pct: 0.85
+                          exit_pct: 0.70
+                          max_hold_days: 10
+                          min_hold_days: 2
+                          sl: -0.08
+                          risk_degree: 0.95
+                          notional: 20000
+                          rebalance_band: 0.05
+                          cooldown_days: 3
+                          max_turnover: 0.30
+                  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