Backtesting
Marketing/Content note: Initial scaffolding — expand with annotated screenshots of a real backtest report.
Backtesting runs your strategy against historical market data so you can evaluate it before risking capital.
Reading the metrics
| Metric | What it tells you |
|---|---|
| Sharpe ratio | Risk-adjusted return. Higher is better; compare similar strategies. |
| Maximum drawdown (MDD) | The largest peak-to-trough loss. Lower is better. |
| Win rate | Share of trades that were profitable. |
| Profit factor | Gross profit ÷ gross loss. Above 1.0 is profitable in-sample. |
Avoid common pitfalls
- Overfitting — a strategy tuned perfectly to the past often fails live. Prefer simple rules that generalize.
- Look-ahead bias — make sure rules only use information available at the time of each decision. Horizon's engine is event-driven to prevent this.
- Ignoring costs — fees and slippage matter; factor them into expectations.
warning
Backtested performance is not a prediction. Past results never guarantee future performance.
Next steps
When results look promising, connect a broker and read Going live.