한국프로야구 투수 연봉 평가 척도에 영향을 미치는 경기력 변수 분석 연구

Abstract

Since the concept of Sabermetrics is introduced into the business of baseball industry, several outcomes (i.e., win/loss prediction model and prediction of going playoff) are developed and utilized in the past decade or nowadays. The role of pitcher has been more important than ever and thus the mechanism of performance analysis brought attentions to sport managers. Therefore, the main purposes of this study are (1) to segregate starting pitchers and relievers into some groups abided by K-maens clustering and (2) extract the meaningful factors which would eventually contribute to valuation of their market value, respectively. The performance records and salary information of a total of 2,792 former and ucrrent professional baseball players from 1997 to 2015 were obtained. As results, strikeouts (predictive impotrance = 0.41), age (predictive importance = 0.27), the number of taking the mound by starting pitcher (preidctive importance = 0.26) and FIP (Fielding Independent Pitching and predictive importance = 0.05) were adopted as important factors in K-mean clu-s tering supported by simple regression analysis with artificial neural network of multi-layer perception. Besides, the results by K-means clustering included that can be divided into seven groups and can especially find two groups: Cluster 2 (top-tier starting pitchers) and Cluster 7 (good relievers).