Sign up
All challenges
Most candidates spend 8–14 hours; take what you need.

Quant Screener & Scoring

Design a scoring or screening signal over fundamental data, with a backtest that holds up to scrutiny.

The problem

Real fundamental data is not clean: financials are reported at mixed scales, ratios are sometimes computed incorrectly upstream, shares-outstanding data is corrupt for a meaningful slice of companies, and fields are sparse for smaller caps.

A scoring signal that assumes clean inputs will look impressive on a curated demo set and quietly produce garbage verdicts on the long tail — which is most of the market.

What to deliver

  • A scoring or screening signal over fundamental data (quality, value, momentum, distress — your choice of thesis).
  • A backtest that reports honestly — including where the signal does NOT work, not just where it does.
  • An explicit data-quality layer: how you detect and handle corrupt, missing, or mis-scaled inputs before they poison the score.
  • A short explanation of the signal a non-quant could follow — if you can't explain why a stock scored low, the score isn't usable.

What a good submission looks like

  • Reports weak or negative results honestly rather than curve-fitting a demo.
  • Has explicit guards against known data pathologies (sparse fields, unit-scale mismatches, survivorship bias in the backtest universe).
  • Prioritizes explainability — a black-box score nobody trusts is worse than no score.

We're evaluating

Statistical rigorData-quality handlingBacktest honestyExplainability

How to submit

  1. Build your solution, using any tools or stack you prefer.
  2. Write up your thinking — decisions made, tradeoffs, what you'd do with more time.
  3. Zip your code + write-up, name it yourname-quant-scoring.zip.
  4. Email it to us — the button below pre-fills the subject and a template.