Match Prediction Analysis Based on LGBM Model with Information Gain Decision Tree

DOI

10.2991/978-2-38476-384-9_87How to use a DOI?

Keywords

Logistic regression equation model; LGBM model; chi-square test; Pearson correlation coefficient test; information gain algorithm

Abstract

This study aims to analyze the players’ performance in the competition through the LGBM (LightGBM) based model with the information gain decision tree, with a special focus on the prediction and assessment of momentum change. First, a logistic regression model was constructed to predict momentum changes by selecting key factors as an indicator system through data processing. Subsequently, various algorithms such as LGBM were introduced for comparative analysis, and it was found that the LGBM model performed the best in terms of prediction accuracy and stability, and visualized the momentum of the players’ competitions. Then, chi-square test and Pearson correlation coefficient analysis were used to statistically assess the correlation between the player’s performance and the randomly generated data, and the results showed that the momentum data were significantly affected by multiple factors. In addition, the study evaluated the performance of the model using metrics such as accuracy, recall, precision, F1 score and AUC to emphasize the variation of momentum in different match scenarios. Finally, using an information gain algorithm, the study calculates the characteristic importance of each metric, thus revealing the key factors affecting race momentum.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Baoliang Qiu
AU  - Jintian Lin
AU  - Jiayu Han
PY  - 2025
DA  - 2025/04/03
TI  - Match Prediction Analysis Based on LGBM Model with Information Gain Decision Tree
BT  - Proceedings of the 2024 3rd International Conference on Educational Science and Social Culture (ESSC 2024)
PB  - Atlantis Press
SP  - 767
EP  - 775
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-384-9_87
DO  - 10.2991/978-2-38476-384-9_87
ID  - Qiu2025
ER  -