Back to Community

Feature importance: Shapley values for financial models

BABayesianBull
Feb 8, 2026
1,465 views
10 posts
strategy
interpretability
shap

SHAP values provide a principled way to understand feature importance in ML models.

import shap

explainer = shap.TreeExplainer(model) shap_values = explainer.shap_values(X_test) shap.summary_plot(shap_values, X_test)

Key findings from my analysis:

  • Momentum features (5d, 21d returns) have the highest SHAP values
  • Volatility features are most important during regime transitions
  • Calendar features matter more than I expected (quarter-end effects)

9 Replies

19
ENEnsembleKingFeb 17, 2026

I've found that sector neutrality is a key factor in the scoring. Strategies that are long one sector and short another tend to underperform.

32
BABayesianBullFeb 12, 2026

Thanks for sharing! This is exactly the kind of insight that helps the community grow. Bookmarking this thread.

4
COCovarianceKid2d ago

Has anyone tried using attention mechanisms for this? The temporal attention weights could tell you which historical periods are most relevant.

26
RIRiskQuant2d ago

Anyone else noticing that momentum factors have been working particularly well in the last month of competition data?

38
QUQuantDev426d ago

For those wondering: yes, you can use external Python packages in submissions, but they must be in the approved list. No custom C extensions.

10
ENEnsembleKingFeb 18, 2026

One more thing: the scoring engine uses a held-out test period that you never see. So your validation score is the best you can do.

15
FAFactorZooFeb 11, 2026

The biggest mistake I see newcomers make: optimizing for the wrong metric. Sharpe != best trading strategy. Consider Calmar, Sortino, and max drawdown.

15
MIMicroAlphaFeb 13, 2026

The biggest mistake I see newcomers make: optimizing for the wrong metric. Sharpe != best trading strategy. Consider Calmar, Sortino, and max drawdown.

20
VOVolTraderFeb 14, 2026

Great analysis! I've been using a similar approach with rolling z-scores and it's been working well for mean reversion signals.

39
SHSharpeShooterFeb 24, 2026
edited

For factor models, I'd strongly recommend the Fama-French 5-factor model as a starting point. It captures most systematic risk.

12
MIMicroAlpha6d ago

I disagree about the GARCH approach. In my experience, realized volatility estimators (like the Rogers-Satchell estimator) outperform parametric models.

Post a Reply