Methodology

The luck test (permutation)

We randomly flip the sign of each of your trades thousands of times to build a picture of what 'no real edge' looks like, then measure how far your actual result sits above that. Pure luck lands in the middle; a real edge lands far in the tail.

Probabilistic Sharpe Ratio (PSR)

The probability your true Sharpe is above zero, given how many trades you have and how fat-tailed your returns are. Short, lumpy records get penalised — correctly.

Deflated Sharpe Ratio (DSR)

Your Sharpe, discounted for how many strategy variations you tried. Test 200 versions and keep the best, and an impressive Sharpe can deflate to near zero. This is how we catch overfitting.

Minimum Track Record Length (MinTRL)

How many trades you'd actually need before your Sharpe is believable. Usually far more than people expect — so we tell you when you simply don't have enough data yet.

Monte-Carlo risk of ruin

We resample your own trades thousands of times to estimate your odds of a deep drawdown and the worst drawdown you should expect — then suggest a position size that survives.

The Edge Score

Your headline score combines how decisively you beat luck with how much your evidence survives the overfitting discount, then applies honest penalties for a thin track record or results that lean on one lucky trade. Below 30 trades we refuse to give a confident verdict and mark the report provisional — a brutally honest tool can't hand out a high score on a handful of trades.

Limitations (we'd rather you know)

• We analyse the history you give us. We can't verify the trades were real or live — only that the math on the supplied data is correct.
• Statistics describe the past. They reduce the chance of fooling yourself; they do not predict the future.
• Prop-firm rule sets are generic, user-selectable approximations and may differ from any firm's current rules.