• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.315-316
• /
• 2023

본 논문에서는 딥러닝을 활용하여 KBO (Korea Baseball Organization)의 다음 시즌 플레이오프 진출 확률을 예측하는 Deep Neural Network (DNN) 시스템을 설계하고 구현하는 방법을 제안한다. 연구 방법으로 KBO 각 시즌별 데이터를 1999년도 데이터부터 수집하여 분석한 결과, 각 시즌 데이터 중 경기당 평균 득점, 타자 OPS, 투수 WHIP 등이 시즌 결과에 유의미한 영향을 끼치는 것을 확인하였다. 모델 설계는 linear, softmax 함수를 사용하는 것보다 relu, tanh, sigmoid 함수를 사용했을 때 더 높은 정확도를 얻을 수 있었다. 실제 2022 시즌 결과를 예측한 결과 88%의 정확도를 도출했다. 폭투의 수, 피홈런 등 가중치가 높은 변수의 값이 우수할 경우 시즌 결과가 좋게 나온다는 것이 증명되었다. 본 논문에서 설계한 이 시스템은 KBO 구단만이 아닌 모든 야구단에서 선수단을 구성하는데 활용 가능하다고 사료된다.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.3
• /
• pp.625-633
• /
• 2017

Fielding Independent Pitching (FIP) is a statistic that measure pitcher performance by eliminating plate appearance outcomes that involve defensive play. FIP uses pitcher dependent outcomes such that walks, strikeouts, hit by pitches, and home runs allowed. The FIP equation derived from linear weights uses three coefficients 13, 3, -2 for evaluating Major League Baseball pitchers. However, these coefficients derived from run value of major league baseball are not suitable to Korea Baseball Organization pitchers due to baseball circumstances. In this study, new FIP called kFIP for Korea Baseball Organization pitchers are provided. We recalculate coefficients and get 14, 3, -1 for evaluating Korean Baseball pitchers. As a result, kFIP is statistically significantly better than FIP at predicting pitcher ERA in KBO League.

• The Journal of Asian Finance, Economics and Business
• /
• v.6 no.3
• /
• pp.269-282
• /
• 2019

The purpose of this study is to investigate the relationship between the spectator experience and satisfaction with a focus on attachment and a sense of community. The survey was given to random spectators who watched KBO (The Korea Baseball Organization) games in 2018. With 189 surveyed participants, this study used exploratory factor analysis and reliability analysis to verify the reliability and validity of the measured variables. The hierarchical multiple regression correlation was employed as a statistical method for the hypotheses of this study. The findings showed that spectators' experiences have influences on satisfaction. Among the experience factors, education and entertainment affect attachment, and education has the only significant influence on a sense of community. In addition, spectators' attachment and a sense of community positively influence satisfaction. Attachment and a sense of community have a relatively mediated effect on spectators' experiences and satisfaction. This study confirmed the need for various spectator experiences at KBO games, and the importance of place attachment or a sense of community.

• The Korean Journal of Applied Statistics
• /
• v.29 no.2
• /
• pp.321-330
• /
• 2016

Run expectancy (RE) is the mean number of runs scored from a specific base runner/outs situation of an inning to the end of the inning. Win expectancy (WE) is the probability that a particular team will win the game at a specific game state such as half-inning, score difference, outs, and/or runners on base. In this paper, we derive RE and WE for the Korea Baseball Organization (KBO) League based on six-year data from 2007 to 2012 using a Markov chain model.

• The Korean Journal of Applied Statistics
• /
• v.24 no.1
• /
• pp.169-175
• /
• 2011

Since 2009, a new method of computing the percentage of victories is being used in the regular league of the Korean professional baseball. This method produced enormous results from the first year of application, and also had an effect on the team standings in 2010. In this paper, we have examined the effects this method had on the Korean professional baseball in 2009 and 2010. We also have discussed what the Korea Baseball Organization need to complement in using this method and suggested complementary measures.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.49-61
• /
• 2022

In sports, the proportion of data analysis in team management such as team strategy planning and marketing is increasing. In KBO(Korea Baseball Organization) league, in particular, plans such as recruiting players and fostering players are established to devise team strategies for the next year, such as FA and trade, at the end of a season. For these reasons, it is very important to predict players' performance for the next year. In this study, the target was limited to only the batter and tried to find out how to predict whether the performance of the next year will improve. As a standard record for rising and falling, OPS(On-Base Plus Slugging), which is easy to calculate and has a high relationship with team score, was used. In this study, 40 years of regular season data from 1982 to 2021 were used as data, and 11 machine learning classification models were used as experimental methods. Predicting the rise and fall of OPS, RBF SVM, Neural Net, Gaussian Process, and AdaBoost were more accurate than other classification models, and age did not significantly affect accuracy.

• Journal of Sport and Applied Science
• /
• v.4 no.4
• /
• pp.7-17
• /
• 2020

Purpose: This study started with interest in sport culture and is meaningful as an exploratory study to help with the basic understanding of sport culture research. Research design, data, and methodology: The approach of this study is the exploratory approach by literature reviews. This study carried out exploratory research on thinking about diversity of sports culture and the development process of sports culture by human history periods. Results: First, in thinking about cultural diversity, cultural absolutism and cultural relativism were identified. The characteristics of sports culture can identify universality, individuality and diffusion, and the attributes of sports culture included sharing, learning, accumulation, whole systematic relationship and change. Second, the characteristics of sports culture were identified by the approach of each historical era. The historical stages were divided into ancient civilizations, ancient Greece and Rome, middle ages and early modern period, and late modern period. Sports have historically been found to have a British-centered European origin or popularized in the United States. Conclusions: with the characteristics of modern sports culture, the globalization of sports culture, the prominence of sports industry and sports space marketing, and the symbiotic influence relationship of sports and mass media were examined and future directions were discussed.

• Journal of Sport and Applied Science
• /
• v.5 no.2
• /
• pp.1-7
• /
• 2021

Purpose: This study started with an interest in sports culture-related content and aims to comprehend the application of traditional and contemporary cultural content to sport business. Research design, data, and methodology: The current study reviews related-documents, research papers, media reports, and a secondary data. The collected data were multiple reviewed via content analysis. Results: Findings are as follow. First, the study found that sports is born in religious rituals which are associated with human needs for survival and prosperity. Second, sports is sort of official format that inherent desire of human could be satisfied, representing play and game. Third, the current study discovered that sports could be cultural products such as literature and film. This is because sport has often been used as major themes in contemporary art production. Finally, this study included important cultural content categories, but could not cover all categories due to the limitations of the study. Conclusions: this study reviewed multiple literature to decode historical and anthropological meanings of sport. The finding presents the cultural traits and meaning of contemporary sport. Further implications were discussed.

• The Korean Journal of Applied Statistics
• /
• v.29 no.6
• /
• pp.1095-1106
• /
• 2016

The quantile regression method proposed by Koenker et al. (1978) focuses on conditional quantiles given by independent variables, and analyzes the relationship between response variable and independent variables at the given quantile. Considering the linear programming used for the estimation of quantile regression coefficients, the model fitting job might be difficult when large data are introduced for analysis. Therefore, dimension reduction (or variable selection) could be a good solution for the quantile regression of large data sets. Regression tree methods are applied to a variable selection for quantile regression in this paper. Real data of Korea Baseball Organization (KBO) players are analyzed following the variable selection approach based on the regression tree. Analysis result shows that a few important variables are selected, which are also meaningful for the given quantiles of salary data of the baseball players.