Back to Community

Market impact models for realistic backtesting

DADataSciPro
Jan 19, 2026
1,967 views
19 posts
strategy
market-impact
backtesting

Ignoring market impact in backtests leads to significantly inflated performance, especially for strategies that trade less liquid instruments.

Models to consider:

  • Linear impact: cost proportional to trade size (simplistic)
  • Square-root impact: cost ~ sqrt(volume/ADV), more realistic
  • Almgren-Chriss: optimal execution framework
The AlphaNova scoring engine uses a linear model with 5bps fixed cost. I'd love to see square-root impact for more realistic evaluation.

18 Replies

25
GRGradientHunterFeb 1, 2026
edited

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

3
BABayesianBull4d ago

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

27
BUBugHunter99Jan 20, 2026

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

3
DADataSciProFeb 23, 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.

1
GRGradientHunter1d ago

Be careful with the Kelly criterion for position sizing. Full Kelly is way too aggressive. I use quarter-Kelly in practice.

21
COCovarianceKid6d ago

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

10
BABayesianBull2d ago

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

14
QUQuantDev425d ago

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.

Post a Reply