본문 바로가기
  • Home

A Win/Lose prediction model of Korean professional baseball using machine learning technique

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2019, 24(2), pp.17-24
  • DOI : 10.9708/jksci.2019.24.02.017
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : January 31, 2019
  • Accepted : February 25, 2019
  • Published : February 28, 2019

Yeong-Jin Seo 1 Hyung-Woo Moon 2 Yong-Tae Woo 2

1하이볼
2창원대학교

Accredited

ABSTRACT

In this paper, we propose a new model for predicting effective Win/Loss in professional baseball game in Korea using machine learning technique. we used basic baseball data and Sabermetrics data, which are highly correlated with score to predict and we used the deep learning technique to learn based on supervised learning. The Drop-Out algorithm and the ReLu activation function In the trained neural network, the expected odds was calculated using the predictions of the team's expected scores and expected loss. The team with the higher expected rate of victory was predicted as the winning team. In order to verify the effectiveness of the proposed model, we compared the actual percentage of win, pythagorean expectation, and win percentage of the proposed model.

Citation status

* References for papers published after 2022 are currently being built.