Semtum

Test a strategy, written as one sentence

Load your own prices or practise on made-up ones, describe a rule in one line, and get the equity curve, the placebo sweep, the noise floor and the verdict, with the date it stopped working. Free, nothing to download.

Tool 5 of 5

The other four tools score numbers you bring. This one produces them: pick a market, build a rule from the menus below, and press Test it. It runs the rule, the fair benchmark, the placebo sweep, the settings next to yours and the noise floor, then says what happened and when. Nothing to download, nothing to install.

Watch: what goes in
What it tells you

The same seven conditions the ledger applies to every approach, applied to yours; the seventh, forward data, is one no backtest can meet. With the date it stopped working, if it did. Not whether the rule made money, since a third of arbitrary date windows are profitable, but whether it beat simply holding less, whether the settings next to yours agree, whether random entries with the same count and holding times do as well, and whether doubling the costs ends it.

The best this page can ever say is candidate. It is a backtest, and only forward data can promote one.

Made-up practice prices, so you can learn the tool before finding a file. Each behaves roughly like its kind of market, bear runs included, but none is a real market, and a result on one says nothing about any real one. To test a real market, pick My own file.

Your rule, piece by piece

Where this number comes from

The free first module works through the arithmetic behind this calculator: where the bar comes from, why looking twice raises it, and what to do when your result sits below it. Subscribe for one email every two weeks about what I tested.

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 →

These match the Python toolkit. The noise-floor integration is the same calculation as the toolkit’s own noise floor; the real-money bar here uses the exact closed form where the Python simulates it, so it may differ in the second decimal. Everything runs in your browser; nothing you paste is sent anywhere, and the page works with no internet connection.

This is not financial advice and not a recommendation to buy or sell anything. A result that clears every bar on this page is a reason to collect forward data, not a reason to fund it. See Module 8.