Semtum

Is your backtest real?

Five free calculators that answer it. Four score numbers you already have; the last runs a rule you describe in one sentence. Every one tells you where to get what it asks for. Nothing you type leaves your browser.

Thirty seconds of why this matters

Put a thousand people in a room and give each one a coin. Every morning they flip it: heads they buy, tails they sit in cash, and no skill enters the process at any point.

After two years, one of them has a track record that looks like genius. Not because they were good, but because when a thousand people do something random, the luckiest one looks remarkable. If they posted it online you would follow them. They cannot tell either: from the inside, a lucky streak feels exactly like skill.

The same thing happens inside your own testing. You tried a 20-day average, then 50. You added a stop, then moved it. You changed the asset, then the start date. Each of those was a coin flipper, and by the time something finally worked you may have taken forty draws, and the best of forty random draws looks good.

That is not cheating. It is what everyone does. But it means your result has to beat a bar that rises every time you look, and almost nobody calculates that bar. These tools calculate it.

Before you go any further

If one of these told you something uncomfortable, the free first module explains the arithmetic behind it in full. Subscribe for one email every two weeks: what failed and why, and the rare one that survived.

Your address is used for this and nothing else. Every email has a one-click unsubscribe.

If a tool here told you something uncomfortable

Why your backtest lied to you

The free first module explains the arithmetic behind these calculators in full: where the bar comes from, why looking twice raises it, and what to do when your result sits below it. No signup, ~14 minutes.

Read it free

The full course is eight modules, nineteen data sources with the trap in each, twelve working download scripts and the searchable ledger of every approach I tested, one of which survived. See what is in it →