Paper: arXiv 2307.13807
Authors: Vélez Jiménez, Román Alberto, Lecuanda Ontiveros, José Manuel, Edgar Possani
Abstract
This paper presents a novel approach for optimizing betting strategies in sports gambling by integrating Von Neumann-Morgenstern Expected Utility Theory, deep learning techniques, and advanced formulations of the Kelly Criterion. By combining neural network models with portfolio optimization, our method achieved remarkable profits of 135.8% relative to the initial wealth during the latter half of the 20/21 season of the English Premier League. We explore complete and restricted strategies, evaluating their performance, risk management, and diversification. A deep neural network model is developed to forecast match outcomes, addressing challenges such as limited variables. Our research provides valuable insights and practical applications in the field of sports betting and predictive modeling.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 7.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced mathematical concepts like Von Neumann-Morgenstern utility, deep learning architecture details, and detailed portfolio optimization formulations (Kelly Criterion, Sharpe Ratio), and presents specific backtest results (135.8% profit) on a defined dataset (English Premier League).
Research Flowchart
flowchart TD
A["Research Goal: Optimize Sports Betting Strategy"] --> B["Data: EPL 20/21 Season Match Data"]
B --> C["Methodology: Deep Neural Network Model"]
C --> D{"Forecast Match Outcomes"}
D --> E["Computational Process:<br>Portfolio Optimization &<br>Kelly Criterion Allocation"]
E --> F["Key Findings:<br>135.8% Profit Increase<br>Risk-Managed Diversification"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a novel approach that combines expected utility theory, deep learning, and advanced Kelly Criterion formulations to optimize betting strategies.
Source sentence
This paper presents a novel approach for optimizing betting strategies in sports gambling by integrating Von Neumann-Morgenstern Expected Utility Theory, deep learning techniques, and advanced formulations of the Kelly Criterion.
Assumes 6
- All wagers result in a positive return (W1 > 0). market
Source sentence
It is assumed that all wagers result in a positive return, that is, W1 > 0.
- Odds and probabilities of events are fixed over time. market
Source sentence
It is assumed that the odds and probabilities of the events are fixed over time.
- No short selling or borrowing; money is infinitely divisible with no minimum bet requirement. execution
Source sentence
The analysis assumes certain conditions regarding the nature of the betting system. Specifically, it assumes the absence of short selling and borrowing, and assumes that money is infinitely divisible with no minimum bet requirement.
- Each wager amount ℓi is non‑negative (ℓi ≥ 0). execution
Source sentence
First, it is implied that the wager amount ℓi for each event i is non‑negative (ℓi ≥0) for all i.
Show 2 more
- Total wager across all events does not exceed total wealth (Σi ℓi ≤ 1). execution
Source sentence
Second, the assumption is made that the total wager across all events satisfies the constraint
- Data from the first matchweek of each season are excluded due to high uncertainty. data
Source sentence
It is important to note that observations for teams on the first matchweek of each season were removed from the dataset.
Data
English Premier League betting · other
- EA Sports ratings alternative public
Source sentence
were utilized to assess the overall quality, offense, midfield, and defense of teams on a weekly basis.
- Understats database fundamentals public
Source sentence
The Understats database provides match‑level data for each team in the English Premier League.
- Match odds from multiple bookmakers other public
Source sentence
match odds from multiple bookmakers, obtained through Football Data U.K..
Costs
Modeled
Commission (track take) tt is included; tt may be negative, affecting gross return R(ℓA)=1/(1+tt).
Source sentence
where the tt is known as the commission (commonly known as track take) that a casino charges. Therefore tt > 0. However, since the betting market is a non‑efficient market
Finds 3
total return 135.8%
- The proposed method achieved a profit of 135.8% relative to initial wealth during the latter half of the 2020/21 EPL season. performance
Source sentence
our method achieved remarkable profits of 135.8% relative to the initial wealth during the latter half of the 20/21 season of the English Premier League.
- Multinomial regression on the reduced variable set attained 41.76% accuracy (cross‑entropy 1.34), while using all variables gave 51.76% accuracy (cross‑entropy 1.22). predictive-accuracy
Source sentence
the multinomial regression model trained on this reduced set of variables achieved a predictive accuracy of 41.76% and a cross‑entropy value of 1.34. In contrast, when trained on the complete set of variables, the model achieved an accuracy of 51.76% and a cross‑entropy value of 1.22.
- When the market commission tt is negative, the gross return under the arbitrage strategy satisfies R(ℓA)=1/(1+tt) > 1, and the Sharpe ratio becomes positively infinite. theoretical
Source sentence
... the Sharpe Ratio is positively infinite, as the numerator is positive and the
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 14 related papers). Coverage is partial, so this is neither replication nor refutation.
1 paper in the archive : Sizing the bets in a focused portfolio
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.