start experiment 44 (exp/44-q12-long-horizon-22d-label-paired-with-w)

2026-08-20 03:55:47 +00:00
parent fd5382caa4
commit 25b4e59295
37 changed files with 3075 additions and 0 deletions
@@ -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