Predicting Competitive Table Tennis Match Outcomes Using Elo and Set-Weighted Elo Rating Systems

Divit Saraf

Predicting Competitive Table Tennis Match Outcomes Using Elo and Set-Weighted Elo Rating Systems

Author(s)	Mr. Divit Saraf
Country	India
Abstract	Accurate prediction of table tennis match outcomes is an important challenge in sports analytics. This study investigates whether an Elo-based rating system can effectively predict competitive table tennis match outcomes and whether incorporating set-score dominance into the rating update improves predictive performance. A dataset comprising 7,851 matches involving 565 players was analysed using two models: a Standard Elo model and a proposed Set-Weighted Elo model, in which the K-factor varied according to the match score (3–0, 3–1, or 3–2). The models were evaluated using prediction accuracy, Brier Score, calibration error, and McNemar's Test. The Standard Elo model achieved an accuracy of 56.31%, while the Set-Weighted Elo model achieved 56.55%. However, the improvement was not statistically significant (McNemar's p = 0.458). Although the Set-Weighted model produced a marginally higher accuracy, it exhibited poorer calibration, indicating less reliable probability estimates. The findings demonstrate that the Standard Elo model provides a practical quantitative framework for predicting competitive table tennis matches, while incorporating set-score dominance into the rating update offers limited predictive benefit under the methodology adopted in this study. Future work may investigate alternative weighting schemes and parameter optimisation to further enhance predictive performance.
Keywords	Table Tennis, Elo Rating System, Sports Analytics, Match Prediction, Machine Learning, Statistical Modelling, Brier Score, McNemar's Test.
Field	Computer > Data / Information
Published In	Volume 8, Issue 4, July-August 2026
Published On	2026-07-24

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Predicting Competitive Table Tennis Match Outcomes Using Elo and Set-Weighted Elo Rating Systems

Share this