Performance analysis
Expectancy and the distribution of returns
Learn why the average trade, dispersion, streaks, and tail outcomes matter more than a single headline percentage.
Average outcome is only the beginning
Expectancy estimates the average profit or loss per trade after the chosen costs. It combines win frequency, average win, average loss, and sometimes commissions or slippage. A positive average does not mean every month or sequence will be positive.
The distribution around the average determines how uncomfortable the path can be before the long-run estimate has a chance to appear.
Study the shape of outcomes
Look at median trade, percentiles, largest wins and losses, consecutive losses, and how much of the result comes from the best few trades. A strategy with a positive mean but a long right tail needs enough capital and patience to survive ordinary periods without those large outcomes.
- Compare mean and median rather than using mean alone.
- Measure the longest losing and winning streaks.
- Review results by month, year, symbol, and session.
- Stress the effect of removing or delaying the best trades.
Connect expectancy to risk
A strategy's trade expectancy does not specify a safe position size. Size determines the account-level distribution, drawdown, and probability of a damaging sequence. Evaluate the same strategy across several risk levels before choosing an operating range.
If the return profile only looks attractive at a risk level that makes the normal losing streak unacceptable, the strategy is not ready for that use.
Discuss this article
Ask a setup question, share a backtest, or compare notes with other algorithmic traders. Use a display name; your email remains private.
Create an account or sign in above to join the conversation.
Loading discussion…