• Journal of the Korean Data and Information Science Society
• /
• 제28권2호
• /
• pp.317-326
• /
• 2017

한국프로야구에서 투수들의 연봉을 결정하는 중요한 요인들을 선형회귀모형을 통해서 살펴본다. 제안된 모형을 이용하여 투수들의 경기력과 연봉간의 패턴을 분석할 수 있으며, 구단 별로 차이점도 알 수 있다. 사용된 데이터는 2010년부터 2015년까지의 투수 기록과 다음 해의 연봉 자료를 이용하였으며, 고려된 설명변수들은 해당연도, 팀의 종류, 게임 수, 평균자책점, 수비무관 평균자책점, 이닝당 안타 및 볼넷 허용률, 대체선수 대비 승리기여도, 선발출장 게임의 수, 승, 패, 세이브, 투구 이닝수, 자유계약선수 여부, 나이, 경험연수이며 반응변수로는 연봉에 로그를 취한 로그연봉을 사용하였다. 그 결과 선발투수이며 경기수가 많고 승수가 많은 투수들에게 많은 연봉이 지급되고 있고 투수의 고유능력을 평가할 수 있는 기록들은 반영이 작게 되고 있음을 확인할 수 있었으며 연구의 결과는 연봉 결정에 중요한 참고자료로 활용될 수 있을 것으로 간주된다.

• 한국컴퓨터정보학회논문지
• /
• 제24권1호
• /
• pp.41-47
• /
• 2019

In this paper, we propose a new batter evaluation model that reflects the skill of the opponent pitcher in Korean professional baseball. The model consists of evaluation factors such as Run Value, Contribution Score and Ball Consumption considering the pitcher grade. These evaluation factors are calculated as different data. In order to include the evaluation factors having different characteristics into one model, each evaluation factor is weighted and added. The genetic algorithms were used to calculate the weights, and the data were based on the 2016 records of Korea Professional Baseball and the salary data of the players of 2017. As a result of calculation of the weight, the weight of the Run Value was high and the weight of the Contribution Score was very low. This means that when calculating the annual salary, it reflects much of the expected score according to the batting result of the batter. On the other hand, the contribution score indicating the degree to which the batting result contributed to the victory of the team according to the state of the economy is not reflected in the salary or point system.

• 대한산업공학회지
• /
• 제40권1호
• /
• pp.8-17
• /
• 2014

In this research, we employed various data mining techniques to build predictive models for win-loss prediction in Korean professional baseball games. The historical data containing information about players and teams was obtained from the official materials that are provided by the KBO website. Using the collected raw data, we additionally prepared two more types of dataset, which are in ratio and binary format respectively. Dividing away-team's records by the records of the corresponding home-team generated the ratio dataset, while the binary dataset was obtained by comparing the record values. We applied seven classification techniques to three (raw, ratio, and binary) datasets. The employed data mining techniques are decision tree, random forest, logistic regression, neural network, support vector machine, linear discriminant analysis, and quadratic discriminant analysis. Among 21(= 3 datasets${\times}$7 techniques) prediction scenarios, the most accurate model was obtained from the random forest technique based on the binary dataset, which prediction accuracy was 84.14%. It was also observed that using the ratio and the binary dataset helped to build better prediction models than using the raw data. From the capability of variable selection in decision tree, random forest, and stepwise logistic regression, we found that annual salary, earned run, strikeout, pitcher's winning percentage, and four balls are important winning factors of a game. This research is distinct from existing studies in that we used three different types of data and various data mining techniques for win-loss prediction in Korean professional baseball games.

• 산업경영시스템학회지
• /
• 제45권2호
• /
• pp.30-36
• /
• 2022

This study analyzed the relationship between efficient pitchers and teams advancing to the postseason in Korean professional baseball through DEA. A total of 1,133 pitchers who threw more than one inning from the 2014 season to the 2018 season were selected for this study. For DEA analysis, input variables were selected as annual salary and inning output variables as Wins, Saves, and Holds and the number of efficient pitchers for each season was classified using the input-oriented BCC model. After that, it was divided into two groups based on joining the postseason or not, and the number of efficient pitchers was compared through a prop test. As a result of the analysis, the groups that advanced to the postseason in the rest of the season except for the 2014 and 2017 seasons had more efficient pitchers. Considering that the 2014 season recorded the highest WAR (Wins Above Replacement) at 183.56 compared to other seasons, most pitchers threw well, and in the 2017 season, they made more mistakes in pitching than in other seasons, but they performed well in batters. The results of this study have expanded the research field using efficiency analysis in professional baseball and can be used as useful data for practical research.