WickCheck / Trading school / Out-of-sample data

Out-of-sample dataIntermediate

Data your strategy was not built or tuned on, kept aside for an honest check.

What it means

Build and tweak on, say, 2015–2021, then run once on 2022–2025. If the results collapse, the edge was probably fitted to the past.

How to spot it

Common mistakes

Related terms

OverfittingTuning a strategy so closely to past data that it captures noise instead of a re…Walk-forward testOptimising on one period, then testing the result on the next unseen period, rep…Sample sizeHow many trades a result is based on. Small samples can look great or terrible b…
Why most strategies need a human behind the screen

What a mechanical test can and cannot tell you about smart money concepts.

Read the lesson

Education only, not financial advice. Definitions vary between teachers; these are ours, written for clarity.

One tested strategy a week

A popular strategy backtested on real data, with the honest numbers. Free, one email a week, unsubscribe any time.