Beating the bookies with their own numbers – and how the online sports betting market is rigged
Lisandro Kaunitz, Shenjun Zhong, Javier Kreiner · arXiv preprint
Main finding
The authors report that the strategy was profitable in a historical simulation, in a simulation on more granular odds data and in a short real-money trial, and that bookmakers restricted their accounts during the trial.
Limitations
Not peer reviewed; small real-money sample; historical odds may not have been executable; account restrictions capped stakes.
Study details
- Authors
- Lisandro Kaunitz, Shenjun Zhong, Javier Kreiner
- Published
- 2017
- Venue
- arXiv:1710.02824 (statistics, applications)
- Status
- Preprint — not peer reviewed
- Evidence type
- Preprint
- Evidence strength
- Limited (our assessment of how much weight the finding can bear)
- Sport
- Association football (many leagues worldwide)
- Markets
- Online bookmaker match-result odds
- Method
- No outcome model: the average of many bookmakers' odds is treated as a probability estimate, and bets are placed only when one bookmaker's price is far enough above that consensus.
- Sample
- Roughly a decade of historical odds plus a short live trial (see paper).
- Replication
- Code and data were released publicly; we found no formal published replication.
Read the original
https://arxiv.org/abs/1710.02824 (opens in a new tab)
Our summary is an original paraphrase for education. Verification: Bibliographic record checked against publisher, index or author listings. No journal version was found. Checked 2026-10-25.