Learn

Understand the numbers.
Ask better questions.

How the ratings are built, how to read a trap statistic, what we measured against the professionals, and how to test a system without fooling yourself. Every number has a source line.

Fundamentals

Ratings and probabilities: two different questions

What a rating says about a runner, what a probability says about uncertainty, and why a 30% chance still leaves 70% for the rest of the field.

2 min readRead ↗

Evidence

How to read a model's record without being dazzled

When the prediction existed, what the denominator is, whether the chances are calibrated, and why winning more often is not the same as making money.

2 min readRead ↗

Track research

A trap-bias percentage needs a second question

What sits under a trap win percentage: the sample, the window, the fair share and whether the pattern survives a period that was not used to find it.

2 min readRead ↗

Fundamentals

How we rate a race

The unique elements behind a TrapMetrics race page, in plain English: point-in-time features, a calibrated chance, the TMR scale, measured going, track geometry, selection classes and the consensus forecast.

6 min readRead ↗

System Builder

The System Builder (and why there is no button that finds the best rule)

Sixty-four elements, five years of results, and a back-tester built to refuse to flatter you: holdout, walk-forward, intervals, Trim, Frontier, staking, and no Goal Seek by design.

6 min readRead ↗

Evidence

Timeform, the Racing Post and us: what we measured

We use the professional forecasts every day and we measured ourselves against them. The rating beats the Timeform forecast on held-out racing; the market beats everyone; the blend of all three lands the most forecasts. All of it is published.

4 min readRead ↗

Fundamentals