A statistical theory of optimal decision-making in sports betting
Open accessThe DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index; none of the 15 sources its claims cite is checked for support yet.
Abstract
The recent legalization of sports wagering in many regions of North America has renewed attention on the practice of sports betting. Although considerable effort has been previously devoted to the analysis of sportsbook odds setting and public betting trends, the principles governing optimal wagering have received less focus. Here the key decisions facing the sports bettor are cast in terms of the probability distribution of the outcome variable and the sportsbook's proposition. Knowledge of the median outcome is shown to be a sufficient condition for optimal prediction in a given match, but additional quantiles are necessary to optimally select the subset of matches to wager on (i.e., those in which one of the outcomes yields a positive expected profit). Upper and lower bounds on wagering accuracy are derived, and the conditions required for statistical estimators to attain the upper bound are provided. To relate the theory to a real-world betting market, an empirical analysis of over 5000 matches from the National Football League is conducted. It is found that the point spreads and totals proposed by sportsbooks capture 86% and 79% of the variability in the median outcome, respectively. The data suggests that, in most cases, a sportsbook bias of only a single point from the true median is sufficient to permit a positive expected profit. Collectively, these findings provide a statistical framework that may be utilized by the betting public to guide decision-making.
Overview
CoChat Summary
TL;DR
The paper develops a statistical framework for optimal sports-betting decisions, showing that the median outcome and nearby quantiles determine when to bet, which side to choose, and when to avoid wagering. Using 5,412 NFL regular-season games from 2002–2022, it finds sportsbooks’ point spreads and totals explain 86% and 79% of the variability in the median outcome, and that in many cases a 1-point bias from the true median is enough to permit positive expected profit.
Key findings
- For point-spread betting, the bettor should wager on the home team if and only if the spread is less than the relevant quantile of the margin of victory; with equal payouts (typical 0.91), this becomes a rule based on the median margin of victory.
- A positive expected profit is only possible if the sportsbook’s spread lies outside the interval between the 0.476 and 0.524 quantiles; for standard 4.5% commission, if the spread is within 2.4 percentiles of the true median, wagering yields negative expected profit.
- In NFL data, sportsbook point spreads explained 86% of the variability in the true median margin of victory (r² = 0.86, n = 21), with OLS slope 0.93 and intercept -0.41; sportsbook point totals explained 79% of the variability in the median point total (r² = 0.79, n = 24).
- For the largest stratified NFL samples, a deviation of only 1 point from the true median was enough to permit positive expected profit in point-spread betting and in point-total betting; across all stratifications, expected profit increased with 1-, 2-, and 3-point deviations, e.g. spread overestimation by 1/2/3 points yielded 0.022 ± 0.011, 0.090 ± 0.021, and 0.15 ± 0.030 expected profit.
Methods
- The paper develops a theoretical model of point-spread, moneyline, and over-under betting using the outcome distribution and sportsbook proposition, deriving theorems/corollaries for optimal side selection, when to wager, and error bounds.
- Empirical analysis uses historical NFL regular-season games from 2002–2022 (n = 5,412), with sportsbook point spreads, point totals, payouts, and consensus values; for spread and total analyses, matches were stratified by sportsbook line into groups with at least 100 matches each.
- Quantiles and medians were estimated with kernel density estimation (Gaussian kernel, bandwidth 2), confidence intervals used 1,000 bootstrap resamples, and relationships between sportsbook lines and medians were assessed with ordinary least squares regression.
Limitations
- The paper states it does not propose or analyze specific predictors/features or models; it focuses on the wagering theory rather than forecasting models.
- The empirical validation is limited to NFL regular-season games; the text notes that outcomes and quantiles may differ across sports such as the NBA.
- The stratification process did not account for varying payouts (for example, -110 vs -105), which the paper says likely introduces negligible error but is still a simplifying assumption.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures


![Fig 3 Do sportsbook point totals deviate from the 0.476-0.524 interval? The 0.476 and 0.524 quantiles of the true point total were estimated for each stratified sample of NFL matches. For all but one stratification (t = 47, 95% confidence interval [41.59-45.42], sportsbook overestimates the total), the confidence intervals of the sample quantiles contained the sportsbook proposition. Visual inspection of the data suggests that, in the NFL betting market at least, sportsbooks are very adept at proposing totals that fall within the critical 0.476-0.524 quantiles.](https://figures.cochat.ai/paper-figures/3a228df2a1b34f14aa756e975a5dc59e/a-statistical-theory-of-optimal-decision-making-in-sports-betting-figure-3.jpg)
![Fig 4 How large of a bias in the point spread is required for positive expected profit? In order to estimate the magnitude of the deviation between sportsbook point spread and median margin of victory that is required to permit a positive profit to the bettor, the hypothetical expected profit was computed for point spreads that differ from the true median by 1, 2, and 3 points in each direction. The analysis was performed separately within each stratified sample, and the figure shows the results of the four largest samples. For 3 of the 4 stratifications, a sportsbook bias of only a single point is required to permit a positive expected return (height of the bar indicates the expected profit of a unit bet assuming that the bettor wagers on the side with the higher probability of winning; error bars indicate the 95% confidence intervals as computed with the bootstrap). For a sportsbook spread of s = 3 (dark black bars), the expected profit on a unit bet is 0.021 [0.008-0.035], 0.094 [0.067-0.119], and 0.166 [0.13-0.2] when the sportsbook’s bias is +1, +2, and +3 points, respectively (mean and confidence interval over 500 bootstrap resamples).](https://figures.cochat.ai/paper-figures/990a8291a6f74a5ca5244935e9a227d6/a-statistical-theory-of-optimal-decision-making-in-sports-betting-figure-4.jpg)
![Fig 5 How large of a bias in the point total is required for positive expected profit? Vertical axis depicts the expected profit of an over-under wager, conditioned on the sportsbook’s posted total deviating from the true margin by a value of 1, 2, or 3 points (horizontal axis). The analysis was performed separately for each unique sportsbook total, and the figure displays the results for the four largest samples. A deviation from the true median of a single point permits a positive expected profit in all four of the depicted groups. For a sportsbook total of t = 44 (green bars), the expected profit on a unit bet is 0.015 [0.004-0.028], 0.075 [0.053-0.10], and 0.13 [0.10-0.17] when the sportsbook’s bias is +1, +2, and +3 points, respectively (mean and confidence interval over 500 bootstrap resamples).](https://figures.cochat.ai/paper-figures/1ce48947255149d8a0da90f0c995ab68/a-statistical-theory-of-optimal-decision-making-in-sports-betting-figure-5.jpg)
Verification
Claims the paper makes
0 Valid · 4 Not valid · 8 Not checked · 96 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Both the slope (0.93, 95% confidence interval [0.81,1.04]) and intercept (-0.41, 95% confidence interval [-1.03,0.16]) of the ordinary least squares (OLS) line of best fit (dashed blue line) indicate a slight overestimation of the margin of victory by the point spread.”
§ A statistical theory of optimal decision-making in sports betting > Results > Empirical results from the National Football League
hedgedstates an associationn = 21- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This is most apparent for positive spreads (i.e., a home favorite).”
§ A statistical theory of optimal decision-making in sports betting > Results > Empirical results from the National Football League
plainstates an associationn = 21- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The distribution of observed point totals for matches with a sportsbook total of τ = 46 is shown in Fig 1b, where the computed median of 44.45 (95% confidence interval [42.25,46.81]) is suggestive of a slight overestimation of the true total.”
§ A statistical theory of optimal decision-making in sports betting > Results > Empirical results from the National Football League
hedged- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Combining data from all samples, the sportsbook point total explained 79% of the variability in the median point total (r2 = 0.79, n = 24; Fig 1d).”
§ A statistical theory of optimal decision-making in sports betting > Results > Empirical results from the National Football League
plainstates an associationn = 24- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For the majority of samples, the confidence intervals of the 0.476 and 0.524 quantiles contained the sportsbook spread.”
§ A statistical theory of optimal decision-making in sports betting > Results > Empirical results from the National Football League
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
73 more claims
Create a free account to see all 108 claims and to verify the 2 references still open.
- It may state two separate claims as one. 20
- Probably not a substantial claim. 13
- The quote only partly states this claim. 1
Citations
Cites
Efron, B., & Tibshirani, R. (1986) · Statistical Science · doi:10.1214/ss/1177013815 · Cited by 6,033
A Probabilistic Theory of Pattern Recognition
Devroye, L., Györfi, L., & Lugosi, G. (1996) · Stochastic Modelling and Applied Probability · doi:10.1007/978-1-4612-0711-5 · Cited by 3,274
A New Interpretation of Information Rate
Kelly, J. L. (1956) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1956.tb03809.x · Cited by 1,586
Handbook of Quantile Regression
(2017) · doi:10.1201/9781315120256 · Cited by 392
Why are Gambling Markets Organised so Differently from Financial Markets?
Levitt, S. D. (2004) · The Economic Journal · doi:10.1111/j.1468-0297.2004.00207.x · Cited by 377
Explaining the Favorite–Long Shot Bias: Is it Risk-Love or Misperceptions?
Snowberg, E., & Wolfers, J. (2010) · Journal of Political Economy · doi:10.1086/655844 · Cited by 316
A machine learning framework for sport result prediction
Bunker, R. P., & Thabtah, F. (2019) · Applied Computing and Informatics · doi:10.1016/j.aci.2017.09.005 · Cited by 300
Using ELO ratings for match result prediction in association football
Hvattum, L. M., & Arntzen, H. (2010) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2009.10.002 · Cited by 288
Testing Market Efficiency: Evidence From The NFL Sports Betting Market
GRAY, P. K., & GRAY, S. F. (1997) · The Journal of Finance · doi:10.1111/j.1540-6261.1997.tb01129.x · Cited by 219
Odds-setters as forecasters: The case of English football
Forrest, D., Goddard, J., & Simmons, R. (2005) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2005.03.003 · Cited by 212
Spann, M., & Skiera, B. (2009) · Journal of Forecasting · doi:10.1002/for.1091 · Cited by 190
Testing the Wisdom of Crowds in the field: Transfermarkt valuations and international soccer results
Peeters, T. L. P. R. (2017) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2017.08.002 · Cited by 182 · cited 1×
“Research into sports betting has also revealed insights into the utility of the “wisdom of the crowd” [14–16], the predictive power of market prices [17–20], quantitative rating systems [21, 22], and the important finding that sportsbooks exploit public biases to maximize their profits [13, 23].”
Testing Rationality in the Point Spread Betting Market
GANDAR, J., ZUBER, R., O'BRIEN, T., & RUSSO, B. (1988) · The Journal of Finance · doi:10.1111/j.1540-6261.1988.tb02617.x · Cited by 181
Information and efficiency: an empirical study of a fixed odds betting market
Kuypers, T. (2000) · Applied Economics · doi:10.1080/00036840050151449 · Cited by 172
Beating the Spread: Testing the Efficiency of the Gambling Market for National Football League Games
Zuber, R. A., Gandar, J. M., & Bowers, B. D. (1985) · Journal of Political Economy · doi:10.1086/261332 · Cited by 144
Intuitive Biases in Choice versus Estimation: Implications for the Wisdom of Crowds
Simmons, J. P., Nelson, L. D., Galak, J., & Frederick, S. (2011) · Journal of Consumer Research · doi:10.1086/658070 · Cited by 140
The degree of inefficiency in the football betting market Statistical tests
Golec, J. (1991) · Journal of Financial Economics · doi:10.1016/0304-405x(91)90034-h · Cited by 139
Information, Prices and Efficiency in a Fixed-Odds Betting Market
Pope, P. F., & Peel, D. A. (1989) · Economica · doi:10.2307/2554281 · Cited by 127
Predicting the outcomes of National Football League games
Boulier, B. L., & Stekler, H. O. (2003) · International Journal of Forecasting · doi:10.1016/s0169-2070(01)00144-3 · Cited by 120
The value of statistical forecasts in the UK association football betting market
Dixon, M. J., & Pope, P. F. (2004) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2003.12.007 · Cited by 117
A Bradley-Terry type model for forecasting tennis match results
McHale, I., & Morton, A. (2011) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2010.04.004 · Cited by 110
Explaining the Favorite-Longshot Bias: Is it Risk-Love or Misperceptions?Preprint
Snowberg, E., & Wolfers, J. J. (2010) · SSRN Electronic Journal · doi:10.2139/ssrn.1595525 · Cited by 84
Market Efficiency and Football Betting
Pankoff, L. D. (1968) · The Journal of Business · doi:10.1086/295077 · Cited by 83
Koopman, S. J., & Lit, R. (2019) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2018.10.011 · Cited by 79
Efficiency of online football betting markets
Angelini, G., & De Angelis, L. (2019) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2018.07.008 · Cited by 77
Forecasting the outcomes of sports events: A review
Wunderlich, F., & Memmert, D. (2020) · European Journal of Sport Science · doi:10.1080/17461391.2020.1793002 · Cited by 76
Constantinou, A. C., & Fenton, N. E. (2013) · Journal of Quantitative Analysis in Sports · doi:10.1515/jqas-2012-0036 · Cited by 72
Exploiting sports-betting market using machine learning
Hubáček, O., Šourek, G., & Železný, F. (2019) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2019.01.001 · Cited by 67
Online bookmakers’ odds as forecasts: The case of European soccer leagues
Štrumbelj, E., & Robnik‐Šikonja, M. (2009) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2009.10.005 · Cited by 65
The Limits of a Measure of Skewness
Hotelling, H., & Solomons, L. M. (1932) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177732911 · Cited by 62
Fundamentals or Noise? Evidence from the Professional Basketball Betting Market
BROWN, W. O., & SAUER, R. D. (1993) · The Journal of Finance · doi:10.1111/j.1540-6261.1993.tb04751.x · Cited by 59
Predicting match outcomes in association football using team ratings and player ratings
Arntzen, H., & Hvattum, L. M. (2020) · Statistical Modelling · doi:10.1177/1471082x20929881 · Cited by 53
The comparative accuracy of judgmental and model forecasts of American football games
Song, C., Boulier, B. L., & Stekler, H. O. (2007) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2007.05.003 · Cited by 49
The Betting Odds Rating System: Using soccer forecasts to forecast soccer
Wunderlich, F., & Memmert, D. (2018) · PLOS ONE · doi:10.1371/journal.pone.0198668 · Cited by 43
Cortis, D. (2015) · The Journal of Prediction Markets · doi:10.5750/jpm.v9i1.987 · Cited by 37
Are Sports Betting Markets Semi-Strong Efficient? Evidence From the COVID-19 Pandemic
Meier, P. F., Flepp, R., & Franck, E. (2021) · International Journal of Sport Finance · doi:10.32731/ijsf/163.082021.01 · Cited by 32
The wisdom of the crowd and prediction markets
Dai, M., Jia, Y., & Kou, S. (2020) · Journal of Econometrics · doi:10.1016/j.jeconom.2020.07.016 · Cited by 20
Are betting returns a useful measure of accuracy in (sports) forecasting?
Wunderlich, F., & Memmert, D. (2020) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2019.08.009 · Cited by 18
An Overview of the Economics of Sports Gambling and an Introduction to the Symposium
Matheson, V. A. (2021) · Eastern Economic Journal · doi:10.1057/s41302-020-00182-4 · Cited by 17
Bernardo, G., Ruberti, M., & Verona, R. (2018) · The Quarterly Review of Economics and Finance · doi:10.1016/j.qref.2018.08.007 · Cited by 16
5. A State-Space Model for National Football League Scores
Glickman, M. E., & Stern, H. S. (2005) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9780898718386.ch5 · Cited by 6
(2020) · doi:10.2139/ssrn.3676515
Research works printed but not linked: 1
- Neal B, Mittal S, Baratin A, Tantia V, Scicluna M, Lacoste-Julien S, et al. A modern take on the bias-variance tradeoff in neural networks. arXiv preprint arXiv:181008591. 2018;.
Cited by
Machine Learning for Soccer Match Result Prediction
Bunker, R., Yeung, C., & Fujii, K. (2024) · Springer optimization and its applications · doi:10.1007/978-3-031-76047-1_2 · Cited by 24
Lu, G. H., Alamri, O. A., Alnssyan, B. S., et al. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.09.049 · Cited by 3
Reichert, R. A., Andrade, F. R. T., Fontelles, M., Reichert, N. C. M., de Almeida, R. M. M., & de MICHELI, D. (2025) · Springer eBooks · doi:10.1007/978-3-031-87986-9_6 · Cited by 2
Skills vs. Luck: Decomposing Deviations from Expected Performance in European Football Leagues
Holzmeister, F., & Johannesson, M. (2025) · Journal of Sports Economics · doi:10.1177/15270025251374620 · Cited by 3
“…on its own but also signi fi cant for managers and executives in the football industry and for understanding both the potential and limitations of using xG data for forecasting future foot-ball games and setting betting odds (e.g., Dmochowski, 2023; Spann & Skiera, 2009; Wunderlich & Memmert, 2018).”
인공지능 기반 스포츠 점수 차 예측의 성과 전환 메커니즘: NBA 핸디캡 이격도 중심의 수익성 실증연구
김, 필., 이, 상., & 전, 성. (2026) · 한국체육학회지 · doi:10.23949/kjpe.2026.5.65.3.7
Metadata
- Authors
- Dmochowski, J. P.
- Affiliations
- City College of New York (US)
- Corresponding author
- Dmochowski, Jacek P.
- ORCID
- Dmochowski, Jacek P.
- Venue
- PLOS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2023-06-28
- Volume
- 18
- Issue
- 6
- Pages
- e0287601
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC10306238
- OpenAlex
- W4382468061
- Cited by
- 5
- References
- 42
- Citations by year
- 2026: 1 · 2025: 2 · 2024: 2
- FWCI
- 1.02
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS ONE (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Sports Analytics and Performance
- Physical Sciences › Mathematics › Statistics and Probability › Probability and Statistical Research
- Social Sciences › Decision Sciences › Management Science and Operations Research › Forecasting Techniques and Applications
- Keywords
- sports betting, point spread, quantiles, expected profit, National Football League
- MeSH terms
- Football, Gambling, Humans, North America
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.