From f9d1fe66f6e4f8ace0d3d774e23f1c79def9bae0 Mon Sep 17 00:00:00 2001 From: zhaoli Date: Thu, 13 Aug 2026 13:21:39 +0000 Subject: [PATCH] exp 11 (sp5d-moment-features): variant C 35-field workflow + result NEGATIVE vs generic-only 19 --- workflows/README-moments.md | 20 ++++ workflows/ablate_generic_moments.yaml | 139 ++++++++++++++++++++++++++ 2 files changed, 159 insertions(+) create mode 100644 workflows/README-moments.md create mode 100644 workflows/ablate_generic_moments.yaml diff --git a/workflows/README-moments.md b/workflows/README-moments.md new file mode 100644 index 0000000..a301ba0 --- /dev/null +++ b/workflows/README-moments.md @@ -0,0 +1,20 @@ +# exp/10 sp5d-moment-features + +Variant C: generic-only 19 + 16 new moment/volatility families (skew, kurt, +DSV+ratios, max_up/down, rv_ac1, rv_cv_22, sig lag-5). 35 sp_* fields, ou/hmm excluded. + +Run a3f7d1d40c3d4b839314fcf5b40f9b08 (tac-rd-moments / exp 12) — FINISHED. + +## Result: NEGATIVE (regression vs generic-only baseline) + +| Metric | generic-only 19 (run 7b1e797) | +moments 35 (run a3f7d1d) | +|---|---|---| +| Rank IC | 0.0635 | 0.0466 | +| Rank ICIR | 0.276 | 0.183 | +| L-S Sharpe | 2.55 | 1.44 | +| net excess (cost) | +3.1% IR 0.28 | -16.2% IR -1.57 | +| MDD | -7.3% | -11.1% | + +Same failure mode as ou/hmm in exp 9: adding cross-sectional moment features +to the 50-name panel degrades the rank signal. Generic-only 19 remains the +best configuration. No further moment-family variants planned. diff --git a/workflows/ablate_generic_moments.yaml b/workflows/ablate_generic_moments.yaml new file mode 100644 index 0000000..0c302b0 --- /dev/null +++ b/workflows/ablate_generic_moments.yaml @@ -0,0 +1,139 @@ +# ----------------------------------------------------------------------------- +# VARIANT C (generic + moments): keeps the winning generic-only 19-field set +# (jump,har,trend,hurst,signature) and adds the NEW generic moment families the +# engine now exposes: +# - realized skewness / kurtosis (sp_rskew_5, sp_rskew_22, sp_rkurt_5, sp_rkurt_22) +# - downside semi-variance + ratios (sp_dsv_1/5/22, sp_dsv_ratio_1/5/22) +# - signed max moves (sp_max_up, sp_max_down) +# - RV autocorr / vol-of-vol (sp_rv_ac1, sp_rv_cv_22) +# - longer-lag signature terms (sp_sig_level2_*_5) +# Drops the model-specific ou/hmm families (they scored high in importance but +# hurt the rank dimension in the all-24 run). Same panel/model as baseline. +# +# Run: +# rd_run_workflow config_path=experiments/workflows/ablate_generic_moments.yaml \ +# experiment_name=tac-rd-moments +# ----------------------------------------------------------------------------- +{%- 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_max_up,sp_max_down,sp_rv1,sp_rv5,sp_rv22,sp_vol_ratio_5_22,sp_vol_ratio_1_22,sp_rv_ac1,sp_rv_cv_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_sig_level2_lead_lag_5,sp_sig_level2_lag_lead_5,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" %} + +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-moments" + +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: "" + 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