• Journal of the Korean Data and Information Science Society
• /
• v.28 no.2
• /
• pp.317-326
• /
• 2017

In this paper, we investigate the effects of performance and non-performance variables attributed to Korean professional baseball pitchers on annual salary by the records about pitchers between 2010 and 2016. We select the variables in reference to previous research related to this topic. The models are then estimated using linear regression model. For pitchers, age, experience in the league, year, eligibility for free agency, the number of wins, WAR, the number of innings pitched, the number of games, the number of saves, the number of games started, and type of baseball team have a statistically significant effect. Among the notable factors, affecting pitchers salaries are largely measure of starting pitchers. Pitcher sabermetrics indexes were poorly reflected on annual salary. The model presented here can be used to remove any unobjective salary differences for Korean professional baseball pitchers.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• 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.

• Journal of Korean Institute of Industrial Engineers
• /
• v.40 no.1
• /
• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.2
• /
• 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.