053 - Martyn Tinsley - 2 of 2 - Walk Forward Correlation: A New Tool for Robust Strategy Design!
Big discount on Martyn's tool for subscribers: https://www.algoadvantage.io/toolbox/Watch Part 1 first! https://youtu.be/Kxvp00VbLx0My detailed write up on Walk Forward Correlation Analysis: https://www.algoadvantage.io/podcast/053-martyn-tinsley-2/Martyn introduces Walk Forward Correlation (WFC) as a diagnostic for two problems that sit at the heart of systematic trading: over-fitting and structural edge. Traditional walk-forward analysis typically optimizes a strategy on an in-sample window, picks the “best” parameter set, then tests that one choice out-of-sample. Used the wrong way, there’s a potential flaw here: one parameter set can look good out-of-sample purely by accident. That tells you very little about whether the underlying model is genuinely robust.Tinsley’s move is simple, but useful. Instead of judging one selected point, he looks at all parameter combinations in the optimisation grid and asks a harder question: does strong in-sample performance tend to map to strong out-of-sample performance across the whole space? If yes, you may have something real. If no, you’re probably flattering noise.Contents:0:00 Walk Forward Correlation Explained 4:22 Best Metrics for Strategy Selection9:27 Building a Combined Performance Metric13:05 Objective Functions and Walk Forward Tests17:30 In-Sample vs Out-of-Sample Validation22:28 Pre-Live Optimization for Live Trading25:14 Why Traditional Walk Forward Falls Short28:59 Walk Forward Correlation Method32:28 Measuring Predictive Power in Trading39:25 Reading Correlation Chart Scenarios41:48 Trade Counts and Statistical Significance45:52 Go/No-Go Gates for Robust Strategies51:03 Optimize Strategy Software Overview56:43 Final Thoughts for Systematic Traders
