Common Backtesting Mistakes
Backtests are useful only when the assumptions are honest and the user looks beyond the biggest return number.
6 min read
Mistake one: judging only by return
A high-return backtest can still be fragile if it has huge drawdowns, too few trades, or unrealistic assumptions.
Always read return with risk.
Mistake two: overfitting
Overfitting happens when a strategy is tuned so tightly to historical data that it may not generalize.
A strategy should make sense economically, not only mathematically.
Mistake three: ignoring execution
Costs, slippage, timing, and liquidity can change outcomes. A backtest should make these assumptions visible.
Key takeaways
- Return without risk is incomplete.
- Overfitting can make a backtest look better than it is.
- Execution assumptions matter.
Common questions
What is look-ahead bias?
Look-ahead bias happens when a backtest uses information that would not have been known at the time of the simulated decision.
How do I reduce overfitting risk?
Use simple rules, test sensible parameter ranges, look for robust regions, and confirm the strategy thesis makes sense.
Put this into practice
Use the lesson as a rule, then test whether the full strategy behaves well.