A framework for applying the Logistic Regression model to obtain predictive analytics for tennis matches

Georgios Friligkos ()

Technium, 2023, vol. 15, issue 1, 60-74

Abstract: In this work, we apply the Logistic Regression (LR) model for predicting the outcome of tennis matches and providing win probability for participating/competing players. Prediction models are classified as machine learning methods, which generate predictions for future scenaria exploiting existing data collections. With the objective to maximize the accuracy of our predictions, we apply the Logistic Regression model under various parameter configurations seeking for an optimal combination of independent variables (features). We present and discuss promising results obtained via the holdout-validation method and the cross-validation method. Furthermore, as a proof of concept of our approach, we designed and implemented a web platform, where users can obtain real-time predictions for tennis matches. Our LR-based framework combined with Artificial Intelligence (AI) can serve as a paradigm in the field of sports analysis for predicting outcomes and evaluating athletic performance.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://techniumscience.com/index.php/technium/article/view/9616/3592 (application/pdf)
https://techniumscience.com/index.php/technium/article/view/9616 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tec:techni:v:15:y:2023:i:1:p:60-74

DOI: 10.47577/technium.v15i.9616

Access Statistics for this article

Technium is currently edited by Scurtu Ionut Cristian

More articles in Technium from Technium Science
Bibliographic data for series maintained by Ana Maria Golita ().