Strategy Optimization, Curve Fitting and Walk Forward Analysis.: Trading System and Portfolio Walk Forward Optimization
Trade Smart Research Developer
Walk-forward optimization is that you optimize the parameter values on a past segment of market data, then test the system forward in time on data following the optimization segment. You evaluate the system based on how well it performs on the test data, not the data it was optimized on.
The process can be repeated by moving the optimization and test segments forward in time. The premise of walk-forward optimization is that the recent past is a better foundation for selecting system parameter values than the distant past. The hope is that the parameter values chosen on the optimization segment will be well suited to the market conditions that immediately follow.
The problem with this approach is that when market conditions change - say, from bull market to bear market - you may find yourself optimizing on one set of market conditions while trading a completely different set of conditions. In this case, there's no good reason to expect that the walk-forward results will be similar to the optimized results.