What is overfitting?Overfitting
Tuning parameters so tightly to past data that the strategy does badly on new data.
Learn “overfitting” in an animated lesson
- Quant BasicsOut-of-Sample Testing: Don't Get Fooled by Backtests
Picking the best settings on historical data is easy. The hard part is whether they still work on data they've never seen. Walk-forward testing mimics the real process of choosing settings first, then trading.
- Oscillators & MomentumSettings and Thresholds: Trading Off Sensitivity
Period 7 or 21? Thresholds of 70/30 or 80/20? Sweep the settings over the same stretch of market and see how the number and quality of signals trade off.
- Indicators in Practice & BacktestingParameter Optimization and Overfitting
Tuning settings to the historical "best" often just memorizes noise. Out-of-sample testing is the real test.
Related terms
See how “overfitting” works for yourself with an animation you can drag and play.
Go to “Out-of-Sample Testing: Don't Get Fooled by Backtests”