Back to Community

How to debug low scoring submissions

BABayesianBull
Jan 25, 2026
1,195 views
8 posts
help
debugging
scoring

My submissions keep scoring below 0.5 Sharpe. I've checked:

  • No look-ahead bias (features use only past data)
  • Predictions are normalized
  • No NaN values
But my local backtest shows 1.8 Sharpe. The discrepancy is huge.

Any tips for diagnosing what goes wrong between local testing and platform scoring?

7 Replies

26
ALAlphaNova TeamFeb 14, 2026

I'd recommend reading "Quantitative Portfolio Management" by Michael Isichenko. It's the best practical guide I've found.

26
FAFactorZooFeb 18, 2026

The data quality in this competition is actually quite good compared to real-world datasets. In practice, you'd spend 60%+ of your time cleaning data.

17
FAFactorZoo2d ago

This is a common pitfall. Make sure your features are computed before the prediction date, not on it. That's subtle look-ahead bias.

20
BUBugHunter99Feb 9, 2026

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

23
NEnewbie_traderFeb 1, 2026

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

4
VOVolTraderFeb 14, 2026

The documentation for the API is at /docs -- it's OpenAPI/Swagger format. Very helpful for understanding submission formats.

Post a Reply