@article{ART003266151},
author={Yubin So and Eunbi Woo and Hanjun Lee},
title={Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2025},
volume={30},
number={11},
pages={311-318}
TY - JOUR
AU - Yubin So
AU - Eunbi Woo
AU - Hanjun Lee
TI - Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development
JO - Journal of The Korea Society of Computer and Information
PY - 2025
VL - 30
IS - 11
PB - The Korean Society Of Computer And Information
SP - 311
EP - 318
SN - 1598-849X
AB - This study presents a Learning-to-Rank (LTR)-based machine learning approach for predicting relative rankings in horse races. Using 9,140 race records from the Korea Racing Authority (May 2024 – April 2025), we evaluate and compare three Gradient Boosted Decision Tree (GBDT) models: LightGBM, XGBoost, and CatBoost. The proposed framework applies the Listwise LambdaRank technique to optimize overall rankings and assesses performance using NDCG, MAP, and MRR metrics. Results show that CatBoost achieved the highest ranking quality (NDCG = 0.8895, MAP = 0.4204), while LightGBM and XGBoost delivered superior prediction accuracy in practical betting scenarios. Feature importance analysis revealed that recent race performance, overall average rank, assigned weight, and horse age are key predictive factors. Finally, we developed a user-friendly web-based prediction system that visualizes ranking results and supports intuitive decision-making, even for novice users. The proposed framework offers a practical and interpretable solution for accurate horse race prediction.
KW - Horse Racing Prediction;Machine Learning;Learning-to-Rank;LambdaRank;;Web-based Prediction System
DO -
UR -
ER -
Yubin So, Eunbi Woo and Hanjun Lee. (2025). Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development. Journal of The Korea Society of Computer and Information, 30(11), 311-318.
Yubin So, Eunbi Woo and Hanjun Lee. 2025, "Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development", Journal of The Korea Society of Computer and Information, vol.30, no.11 pp.311-318.
Yubin So, Eunbi Woo, Hanjun Lee "Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development" Journal of The Korea Society of Computer and Information 30.11 pp.311-318 (2025) : 311.
Yubin So, Eunbi Woo, Hanjun Lee. Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development. 2025; 30(11), 311-318.
Yubin So, Eunbi Woo and Hanjun Lee. "Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development" Journal of The Korea Society of Computer and Information 30, no.11 (2025) : 311-318.
Yubin So; Eunbi Woo; Hanjun Lee. Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development. Journal of The Korea Society of Computer and Information, 30(11), 311-318.
Yubin So; Eunbi Woo; Hanjun Lee. Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development. Journal of The Korea Society of Computer and Information. 2025; 30(11) 311-318.
Yubin So, Eunbi Woo, Hanjun Lee. Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development. 2025; 30(11), 311-318.
Yubin So, Eunbi Woo and Hanjun Lee. "Machine Learning-based Learning-to-Rank Approach for Horse Race Prediction and Web Service Development" Journal of The Korea Society of Computer and Information 30, no.11 (2025) : 311-318.
