Kelly Criterion Calculator

What Kelly does

The Kelly criterion gives the stake size that maximises the long-run growth rate of a bankroll. It scales with your edge: bigger edges get bigger bets, and when the edge disappears the recommended stake goes to zero. It is the only staking method with a mathematical claim to being optimal rather than merely sensible.

The formula

Divide your edge by the odds received. In full: multiply your win probability by the decimal odds minus one, subtract the probability of losing, then divide the whole thing by the decimal odds minus one. The result is the fraction of your bankroll to stake. If it comes out zero or negative, the bet has no edge and the correct stake is nothing.

Why almost nobody bets full Kelly

Full Kelly is optimal only if your probability estimate is exactly right. It never is. Overestimating your edge means systematically overbetting, and Kelly is unforgiving about that: betting twice the Kelly fraction produces zero long-run growth even with a genuine edge. The variance is also brutal, with drawdowns of half your bankroll being routine rather than exceptional.

Half and quarter Kelly

Most serious bettors use a fraction. Half Kelly captures about three quarters of the growth rate with roughly half the volatility, and it gives you room to be wrong about your edge. Quarter Kelly is more conservative again and is a reasonable choice if you are new, if your estimates are untested, or if a large drawdown would affect your decision-making. The cost of being too conservative is slower growth; the cost of being too aggressive is ruin.

When Kelly does not apply cleanly

Kelly assumes one bet at a time with a known edge. Real betting involves correlated positions, several bets live at once, and estimates of unknown accuracy. Treat the output as an upper bound rather than an instruction, and never let a single position exceed a share of bankroll you would be uncomfortable losing entirely.