Kelly criterion

The Kelly criterion is a formula for the fraction of capital to risk on a bet that maximises long-run growth, if the odds are known exactly.

How Kelly criterion is calculated

f* = p - (1 - p) / b, where p is the win probability and b is the payoff per unit risked. With p = 0.55 and b = 1, f* is 0.10, or 10 percent of capital. Because p and b are estimates from past data, errors in them make the formula bet too much, so practitioners use a fraction of it such as half.

How it is read

Kelly describes the growth-optimal size when the inputs are right. Betting more than twice Kelly produces a negative long-run growth rate.

Common mistakes

• Plugging in a backtest win rate as if it were the true probability.
• Using full Kelly. The drawdowns it implies are large even with correct inputs.
• Applying it to trades that overlap or are correlated, where the formula's independence assumption fails.

What Tickfloor tested

Tickfloor's research desk has backtested 678 strategies, net of modelled trading costs. After correcting for the 761 tests run, 0 passed. That does not prove no strategy works. These are historical diagnostics, not validation under Testing Standard v2: the backtest harness predates that standard and has not been re-run to meet it.

• Is Kelly sizing better than volatility targeting? (claim tested)

Lessons that cover it

• Average result per trade, and Kelly sizing

Related concepts

• Position sizing
• Expectancy
• Risk of ruin
• Drawdown
• All concepts

General information only. It doesn't consider your objectives, finances or needs. Tickfloor holds no financial services licence and never places trades.

• See a full worked example (free, no account)
• Browse every course lesson by topic