Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 zhaoli
|
f9d1fe66f6 |
@@ -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.
|
||||
@@ -1,24 +1,22 @@
|
||||
# -----------------------------------------------------------------------------
|
||||
# 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.
|
||||
# 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/exp12_isolation_ensemble.yaml \
|
||||
# experiment_name=tac-rd-rank-ensemble-isolated
|
||||
# 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_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_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 }}"
|
||||
@@ -47,13 +45,13 @@ qlib_init:
|
||||
class: MLflowExpManager
|
||||
module_path: qlib.workflow.expm
|
||||
kwargs:
|
||||
uri: "sqlite:///mlruns.db"
|
||||
default_exp_name: "tac-rd-rank-ensemble-isolated"
|
||||
uri: "sqlite:///{{ LAKE }}/mlruns.db"
|
||||
default_exp_name: "tac-rd-moments"
|
||||
|
||||
task:
|
||||
model:
|
||||
class: RankICEnsembleLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_ensemble
|
||||
class: RankICLGBModel
|
||||
module_path: tac_qlib.contrib.model.rank_gbdt
|
||||
kwargs:
|
||||
loss: mse
|
||||
learning_rate: 0.02
|
||||
@@ -68,7 +66,7 @@ task:
|
||||
subsample_freq: 1
|
||||
reg_alpha: 0.1
|
||||
reg_lambda: 1.0
|
||||
seeds: "42,7,2026,99,123"
|
||||
seed: 42
|
||||
|
||||
dataset:
|
||||
class: DatasetH
|
||||
@@ -80,8 +78,8 @@ task:
|
||||
kwargs:
|
||||
instruments: "{{ UNIVERSE }}"
|
||||
start_time: 2015-01-03
|
||||
end_time: 2026-08-14
|
||||
fit_start_time: 2016-01-04
|
||||
end_time: 2026-08-10
|
||||
fit_start_time: 2015-01-03
|
||||
fit_end_time: 2025-09-01
|
||||
freq: day
|
||||
lake_root: "{{ LAKE }}"
|
||||
@@ -100,7 +98,7 @@ 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]
|
||||
|
||||
Reference in New Issue
Block a user