Back to Community

Handling missing data in financial datasets

RIRiskQuant
Feb 5, 2026
1,135 views
5 posts
help
data-cleaning

The competition dataset has ~3% missing values scattered throughout. How are people handling this?

I've tried:

  • Forward fill (most common for financial data)
  • Interpolation
  • Setting missing = 0 (bad idea for returns)
  • Dropping rows with missing values
Forward fill seems most realistic but it can introduce look-ahead bias if you're not careful.

4 Replies

19
BABayesianBull4d ago

Interesting thread! I've been exploring reinforcement learning for portfolio allocation. The challenge is defining the right reward function.

2
VOVolTrader3d ago

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

7
BABayesianBullFeb 14, 2026

Great discussion! This is why I love this community - knowledge sharing makes everyone better.

32
RERegimeDetectorFeb 21, 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.

13
MIMicroAlphaFeb 21, 2026

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

Post a Reply