Backtesting is the process of testing a trading or investment strategy against historical data to evaluate how it would have performed. It allows you to assess a strategy's risk-adjusted returns, maximum drawdowns, and consistency before committing real capital.
A single-ticker backtest evaluates a strategy on one stock — for example, buying when RSI drops below 30 and selling when it exceeds 70. This is useful for learning but limited. A portfolio-level backtest evaluates a strategy across many stocks simultaneously, which is far more realistic because it accounts for diversification, rebalancing, and capital allocation.
Our platform provides a portfolio-level backtester that tests your strategy across a universe of stocks, simulating the actual experience of managing a real portfolio. This means it handles position sizing, rebalancing frequency, transaction costs, and cash allocation.
This is fundamentally different from single-ticker backtests available on most platforms, which cannot capture how a strategy performs as a cohesive portfolio. Real investing involves selecting from many opportunities, managing multiple positions, and making allocation decisions — portfolio-level backtesting captures all of this.
Overfitting is the most dangerous trap in backtesting — optimizing a strategy so specifically to historical data that it fails in live markets. If a strategy has too many parameters tuned to the past, it is likely overfit.
Other pitfalls include not accounting for transaction costs and slippage, using data with survivorship bias, and testing too short a time period. Walk-forward analysis helps combat overfitting by splitting data into in-sample (for development) and out-of-sample (for validation) periods.
← Back to all investing concepts