# Kelly Criterion **Domain:** Probability / Decision theory **Doc Type:** Developed Wiki Node **Maturity:** Developed **Collection:** [[collections/Gamification|Gamification Collection]] ## Definition The **Kelly criterion** is a rule for sizing repeated wagers to maximize the expected logarithmic growth of capital when probabilities and payoffs are known or estimated. It balances exploitation of an edge against the risk of ruin caused by overbetting. ## Significance Kelly turns prediction into an allocation decision. Its relevance exceeds gambling: any repeated competitive system must distinguish being directionally right from staking so much that uncertainty becomes fatal. Model error remains decisive; a precise formula cannot rescue false probabilities. ## Routes [[wiki/Edward Thorp|Edward Thorp]] · [[wiki/Claude Shannon|Claude Shannon]] · [[wiki/Sports Betting Handle|Sports Betting Handle]] · [[wiki/Prediction Market|Prediction Market]] ## Sources - [[articles/gamification/America Loves Games and the Home Court Advantage|America Loves Games and the Home Court Advantage]] - [J. L. Kelly Jr., A New Interpretation of Information Rate](https://archive.org/details/bstj35-4-917)