Learn to validate a trading strategy.
BacktestGyan is the definitive, free knowledge base on backtesting and quantitative strategy validation for the Indian market — performance metrics, robustness testing, backtesting biases, data quality and the research workflow. Every concept explained answer-first, with original diagrams, formulas and Indian-market examples. Validation science, never signals. Never a promise of profit.
What is backtesting? Backtesting is the process of simulating a fully-specified trading strategy on historical market data to estimate how it would have behaved, so you can study and falsify it before risking capital. Done honestly it needs clean point-in-time data, realistic costs, a benchmark and out-of-sample validation. It is a hypothesis test that reduces uncertainty — not a prediction of future profit.
Why backtesting matters
Backtesting is the cheapest way to falsify a bad idea — before it costs real money — and the only way to quantify a strategy's risk before you live it. Done badly, it is worse than nothing, because a flattering equity curve breeds false confidence. The whole craft is telling an honest test from a lying one.
Falsify cheaply
If an idea loses money even on the friendliest slice of history, it is almost certainly not worth trading. What is backtesting? →
Measure the risk
Drawdown, Sharpe and expectancy tell you how much pain earned the return. Maximum drawdown →
Test that it's real
Walk-forward and out-of-sample testing separate a stable edge from a lucky curve-fit. Walk-forward analysis →
Common myths about backtesting
The beliefs that sink more retail strategies than any market ever did.
Myth: A great backtest means a great strategy.
Reality: A backtest can be tuned to look brilliant on noise and still fail live. Only out-of-sample and forward results carry real evidence.
Myth: A higher win rate is a better system.
Reality: Win rate ignores the size of wins and losses. A 70% win rate can still lose money if the losers are large enough. Expectancy is what counts.
Myth: More data and more optimisation always help.
Reality: Optimising over all your data leaves nothing to validate on, and more parameters make overfitting easier, not the edge stronger.
Myth: If it worked for ten years, it will keep working.
Reality: Markets change regime, liquidity and microstructure. Past robustness is evidence, never a guarantee; that is why forward testing exists.
Explore the knowledge base
Deep, answer-first topic clusters covering the whole science of validating a strategy.
Backtesting Fundamentals
10 pagesBacktesting is the process of simulating a fully-specified trading strategy on historical market data to estimate how it would have behaved, so you c…
Performance Metrics
15 pagesBacktest performance metrics fall into families: return (CAGR, absolute and annualized return), risk-adjusted return (Sharpe, Sortino, Calmar, inform…
Robustness Testing
10 pagesRobustness testing is the set of methods that check whether a backtested edge is stable and real rather than a product of luck or overfitting. It inc…
Backtesting Biases
9 pagesBacktesting biases are systematic errors that make simulated performance look better than a strategy's real edge. The major ones are look-ahead bias …
Choose your learning track
Beginner roadmap
New to backtesting? Build the foundation.
Intermediate roadmap
Know the basics? Measure and validate.
Professional roadmap
Ready for rigour? Stress the edge.
Featured concepts
The ideas that decide whether a backtested edge survives contact with the market.
Run the numbers
Free, private, in-browser calculators — measure your edge, its risk-adjusted return and its worst drawdown.