search for




 

A predictive model for a contract renewal of foreign pitchers in KBO using machine learning
Journal of the Korean Data & Information Science Society 2022;33:963-76
Published online November 30, 2022;  https://doi.org/10.7465/jkdi.2022.33.6.963
© 2022 Korean Data and Information Science Society.

Taeshin Park1 · Jaeyun Kim2

12Department of Big Data Engineering, Soonchunhyang University
Correspondence to: This research was supported by the MSIT(Ministry of Science, ICT), Korea, under the National Program for Excellence in SW, supervised by the IITP(Institute of Information & communications Technology Planning & Evaluation) in 2021(2021-0-01399). This work was supported by the Soonchunhyang University Research Fund.
1 Undergraduate student, Department of Big Data Engineering, Soonchunhyang University, 22, Soonchunhyang-ro, Asan-si, Chungcheongnam-do, 31538, Korea.
2 Assistant professor, Department of Big Data Engineering, Soonchunhyang University, 22, Soonchunhyang-ro, Asan-si, Chungcheongnam-do, 31538, Korea. E-mail: kimym38@sch.ac.kr
Received August 27, 2022; Revised October 30, 2022; Accepted November 2, 2022.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
The Korean Baseball Organization (KBO) introduced a foreign player system to level league power and provide new attractions to baseball fans. In general, teams with good foreign pitching records advance to the post season, and teams with poor score stay in the lower ranks. Only about 34 percent of pitchers have re-signed for the past 11 years, 49 of 143, which shows that it is not easy to scout a good foreign pitcher. Therefore, it can be said that it was a successful scout that the club re-signed with a foreign pitcher. If the club can predict in advance whether a foreign pitcher will renew a contract, which will determine whether or not to join the team in the next season, it can provide high-quality games to baseball fans by recruiting excellent pitchers to raise the level of the KBO league. This paper selects the minor league score of foreign pitchers registered in the KBO, KBO score of the season of joining, face photographs of pitchers, and strike zone heat map image as independent variables. Based on this, we propose a model to predict the contract renewal of foreign pitchers in KBO using principal component analysis and machine learning algorithm.
Keywords : Contract renewal, foreign pitchers, machine learning, predictive model.