Here's a question that sounds technical but has very real money consequences: when a signal provider shows you a backtest, how do you know if it's actually telling you something useful? This is harder than it looks because a backtest that looks brilliant on paper can be completely fabricated — not through dishonesty, but through a process so common it has its own name: overfitting.

Static backtesting means you run a strategy over historical data, tweak the parameters until it performs beautifully, then present those results. The problem? You've essentially memorised the exam answers. The strategy isn't smart — it's just been tuned to fit one specific dataset. Real markets don't hand out the same exam twice.

CONCEPTWalk-forward optimisation tests a strategy on data it has never seen — the only honest measure of genuine edge.
WARNINGA static backtest with suspiciously smooth equity curves is almost always an overfitting red flag — treat it with serious scepticism.
KEY IDEAThe gap between in-sample and out-of-sample performance reveals how much of a strategy's edge is real versus imagined.

Walk-forward optimisation solves this by splitting history into rolling windows. A strategy is optimised on an earlier "in-sample" chunk, then tested immediately on the next "out-of-sample" chunk it has never touched. That test period then becomes history, the window rolls forward, and the process repeats. What you end up with is a chain of genuinely blind tests stitched together — far closer to what live trading actually feels like.

0 +20% +60% Start Mid End Static backtest Walk-forward

When evaluating a signal provider, the methodology behind their track record matters as much as the numbers themselves. A provider showing walk-forward results with honest drawdown periods is demonstrating something real. One showing only in-sample static curves — especially perfectly smooth ones — is showing you a story, not a strategy. Ask specifically: was this tested out-of-sample, and can you see the in-sample versus out-of-sample performance split? Silence or confusion in response to that question tells you everything. For deeper grounding, the concept of overfitting in trading models is worth understanding thoroughly, as is the broader framework of walk-forward optimisation methodology. Traders serious about signal evaluation also benefit from reviewing how backtesting principles apply to systematic strategy validation.

The methodology behind a backtest isn't a footnote — it's the whole story. A pretty equity curve built on static in-sample data is just a well-dressed guess.

This content is for educational purposes only and does not constitute financial product advice. Past performance is not indicative of future results. Profit Logic Ltd (ACN 688 669 936) accepts no responsibility for errors or omissions in this content or anywhere on this website. Always seek advice from a licensed financial adviser before making investment decisions.