Algo Advantage 053 – Martyn Tinsley – Walk Forward Correlation: A New Tool for Robust Strategy Design!

Contributor Podcast

Algo Advantage Episode 053

In this Algo Advantage podcast, host Simon and guest Martyn Tinsley unpack walk-forward correlation – discussing how to validate trading strategies, detect overfitting and make smarter go/no-go decisions before live trading.

The episode is available on Algo Advantage blog: https://algoadvantage.substack.com/p/053-martyn-tinsley-walk-forward-correlation

Excerpt

Test Your Model, Not Its Parameters

“Not everything that counts can be counted, and not everything that can be counted counts.”

That line, usually pinned to Einstein, fits this article rather well. In trading strategy research, we can spend a long time counting the wrong thing: like, as Martyn Tinsley says – whether the single best in-sample parameter set survives out-of-sample testing. Martyn Tinsley’s novel new approach, Walk Forward Correlation, argues that this is often a comforting illusion. Conversely, the traditional approach can also wrongly lead to throwing a potentially profitable strategy away, just because it fails on one parameter set out-of-sample (OOS). What matters is not whether one lucky setting survives, but whether the entire optimisation surface carries information from in-sample to out-of-sample performance.

The setup

Martyn introduces Walk Forward Correlation (WFC) as a diagnostic for two problems that sit at the heart of systematic trading: identifying over-fitting and genuine structural edge. Traditional walk-forward validation typically optimises 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 – for the statisticians out there, because of statistical variance. 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.

Visit Algo Advantage for additional insights on this topic.