Optimal Betting Under Parameter Uncertainty: Improving the Kelly Criterion
Rose D. Baker, Ian G. McHale · Decision Analysis
Main finding
When probabilities are estimated with error, Kelly stakes should be shrunk; shrunken strategies outperformed raw Kelly out of sample in their simulations and tennis illustration.
Limitations
Mainly binary outcomes; the best shrinkage depends on the assumed error model, which bettors rarely know precisely.
Study details
- Authors
- Rose D. Baker, Ian G. McHale
- Published
- 2013
- Venue
- Decision Analysis 10(3), 189–199
- Status
- Published
- Evidence type
- Peer-reviewed theory
- Evidence strength
- Moderate (our assessment of how much weight the finding can bear)
- Sport
- Tennis (empirical illustration)
- Markets
- Bookmaker match odds
- Method
- Decision-theoretic analysis of Kelly betting when the win probability is itself estimated; shrinkage factors are derived and checked by simulation and on tennis betting data.
- Sample
- Tennis matches used as an illustration in the paper.
- Replication
- Unknown.
Read the original
doi:10.1287/deca.2013.0271 (opens in a new tab)
Our summary is an original paraphrase for education. Verification: Bibliographic record checked against publisher, index or author listings. Checked 2026-10-25.