Dynamic graph-based forecasts of bookmakers’ odds in professional tennis
Authors:
Open Access
- 27 May 2026
- journal article
- Published by The Royal Society in Royal Society Open Science
- Vol. 13 (5)
Abstract
Bookmakers’ odds consistently provide one of the most accurate methods for predicting the results of professional tennis matches. However, these odds usually only become available shortly before a match takes place, limiting their usefulness as an analysis tool. To ameliorate this issue, we introduce a novel dynamic graph-based model which aims to forecast bookmakers’ odds for any match on any surface, allowing effective and detailed pre-tournament predictions to be made. By leveraging the high-quality information embedded in these odds, our model incorporates the most up-to-date market assessments of player ability. By analysing major tennis championships from 2024 and 2025, we show that our model achieves comparable accuracy to the bookmakers while significantly outperforming benchmark models on a range of metrics.Keywords
All Related Versions
Funding Information
- Schmidt Fund for Strategic Innovation
- MRC Centre for Global Infectious Disease Analysis
- Danmarks Grundforskningsfond
- Novo Nordisk Fonden
This publication has 15 references indexed in Scilit:
- Price Formation Dynamics and Learning in the Tennis Sports Betting MarketSSRN Electronic Journal, 2025
- A novel comparative study of NNAR approach with linear stochastic time series models in predicting tennis player's performanceBMC Sports Science, Medicine and Rehabilitation, 2024
- Analysis of a double Poisson model for predicting football results in Euro 2020PLOS ONE, 2022
- Comparing Different Data Representations and Machine Learning Models to Predict Tennis2022
- Forecasting Tennis Match Results Using the Bradley-Terry ModelInternational Journal of Photoenergy, 2022
- Weighted Elo rating for tennis match predictionsEuropean Journal of Operational Research, 2022
- Predicting Tennis Match Outcomes with Network Analysis and Machine Learning2021
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- A point-based Bayesian hierarchical model to predict the outcome of tennis matchesJournal of Quantitative Analysis in Sports, 2019
- Matrix Analysis2012