Definition
Backtesting
Backtesting is the process of simulating a trading strategy on historical data to estimate how it would have performed, including returns, drawdowns and risk, before committing real capital.
A rigorous Indian backtest uses clean, survivorship-bias-free price and corporate-action-adjusted data, realistic slippage modelling, exchange charges (STT, stamp duty, brokerage), and proper handling of circuit limits and illiquidity. Sloppy data or look-ahead bias inflate results dramatically.
Backtesting answers what would have happened, but past performance is not a guarantee. The biggest pitfall is overfitting, tuning parameters until the curve looks perfect on history. Disciplined researchers reserve out-of-sample data, use walk-forward analysis, and remain sceptical of strategies that only shine in-sample.
Related terms
- Slippage ModellingSlippage modelling is the quantitative estimation of expected execution costs, including spread, market impact and timing effects, so that a backtest or live strategy reflects realistic, achievable prices.
- Walk-Forward AnalysisWalk-forward analysis is a backtesting technique that repeatedly optimises a strategy on one window of historical data and tests it on the immediately following out-of-sample window, rolling forward through time.
- OverfittingOverfitting, or curve-fitting, occurs when a strategy is tuned so closely to historical data that it captures random noise rather than a genuine pattern, and consequently fails on new data.
- Paper TradingPaper trading is the simulated execution of a strategy in live market conditions using virtual money, allowing a trader to test logic, execution and discipline without financial risk.
Plain-English explainer from The Dispatch Investors Encyclopedia. General information, not financial advice.