Walk-Forward Optimizer
Test Your Trading System On Seen and Unseen Data
Many trading systems fail in the real world because they are built and tested on the same set of historical data.
TradeStation's new Walk Forward Optimizer aids in the mitigation of this problem by performing a set of "walk-forward" performance tests against as-yet-unseen market data, thereby simulating the unpredictability of trading a strategy under real market conditions.
Starting where other optimizing methods typically end, the Walk-Forward Optimizer produces an easy-to-understand, pass-fail analysis of a strategy's key performance criteria
Read Barron's Review of the TradeStation Walk-Forward Optimizer
Figure 1
Rolling Walk-Forward Analysis
In this example, the strategy is optimized on four months of price history and a walk forward analysis is done on eight months of unseen, out-of-sample data, thereby producing a realistic assessment of how well the strategy may perform under actual market conditions.