• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.285-298
• /
• 2012

This research deals with a relationship between the performance of Korean professional baseball players and their annual salaries. It is based on the sabermetrics, which measures the performance of baseball batters in a refined way. We collect the records of batters of eight professional baseball clubs during the season 2009 and 2010. Then, we calculate every index of the sabermetrics. Principal component analysis is used for examining the relationship between those indexes of sabermetrics and annual salary for the next year. In general, batters who show higher performance get more salary. The result of this research can be useful in order to reach an agreement on salary between a player and his club partner.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1501-1509
• /
• 2017

Wins above replacement (WAR) is the most commonly used statistics of the sabermetrics that measure baseball players' abilities. The advantage of a WAR is that it enables to compare performances of players even though they have different roles such as pitcher and hitter. However, WAR is difficult to obtain with common records. Thus, a past studies (Lee and Kim, 2016) suggested the batting ability index to determine the ability of the batter focused on the sabermetrics statistics WAR. In this paper, we selected the best hitter with applying Korea baseball 2016 data based on a proposed model and then observed a total raking of others according to BAI. We are assured that BAI is very excellent statistics through comparing BAI and WAR which is in the spotlight in evaluating performances of players.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.4
• /
• pp.863-874
• /
• 2017

Wins above replacement (WAR) is the most commonly used statistics of the many sabermetrics that measure baseball players' abilities. The advantage of a WAR is that it enables to compare performances of players even though they have different roles such as pitcher and hitter. However, WAR is difficult to obtain with common records. Thus, in this paper, we have calculated the sabermetrics variable based on Korean professional baseball records for the past three years (2014-2016). Using these variables, we suggest starting pitcher ability index that can replace WAR. Starting pitcher ability index was calculated by means of arithmetic mean, weighted average and principal component regression. Then, compared to the WAR, the most relevant method was selected, which would be useful to identify for the starting pitcher ability.

• The Korean Journal of Applied Statistics
• /
• v.29 no.7
• /
• pp.1271-1281
• /
• 2016

Wins above replacement (WAR) is one of the most widely used statistic among sabermatrics statistics that measure the ability of a batter in baseball. WAR has a great advantage that is to represent the attack power of the player and the base running ability, defensive ability as a single value. In this study, we proposed a hitter ability index using the sabermetrics statistics that can replace WAR based on Korea Baseball Record Data of the last three years (2013-2015). First, we calculated Batter ability index through the arithmetic mean method, the weighted average method, principal component regression and selected the method that had high correlation with WAR.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.17-24
• /
• 2019

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.

• The Korean Journal of Applied Statistics
• /
• v.29 no.6
• /
• pp.999-1005
• /
• 2016

The advent of big data brings the opportunity to answer many open scientic questions but also presents some interesting challenges. Main features of contemporary datasets are the high dimensionality and massive sample size. In this paper, we give an overview of major challenges caused by these two features: (1) noise accumulation and spurious correlations in high dimensional data; (ii) computational scalability for massive data. We also provide applications of big data in various fields including forecast of disasters, digital humanities and sabermetrics.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.349-356
• /
• 2014

In baseball, sabermetric batting statistics are used to compare an offensive performance of players. There exist dozens of sabermetric statistics, but baseball fans don't like the complexity of an abundance of measures. This paper provides a batting grade index (BGI) using principal component based on eight batting statistics. These are OPS, ISO, SECA, TA, RC, RC/27, wOBA and XR. We show that how standardized batting statistics are aggregated and weighted to arrive at a single composite measure of BGI. Also our result allows for segmentation of players into groups using the K-means clustering algorithm.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.4
• /
• pp.865-874
• /
• 2015

This research is to comprehensively evaluate offensive abilities of baseball players who are expected to produce as many runs as possible by their hitting and running. To this end, we establish a simulation program to obtain the so-called scoring index of an individual player. The scoring index of a player is defined as an expected number of runs scored by an imaginary team that is composed of nine copies of the player. As a simulation input, we use 2014 season data of Korean pro-baseball. As a result, we present the scoring indices of top 10 players, 9 Korean pro-baseball teams, and overall 2014 season. The scoring index can serve as a comprehensive evaluation of offensive ability of a player or a team, selection of players for a (national) team or for a starting line-up, estimation of player's worth, and so on.

• 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 Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.677-687
• /
• 2016

Among lots of sabermetric statistics for baseball batters' ability, the wins above replacement (WAR) is the most popular statistic in MLB. However, there exists a difficulty applying WAR to KBO, since KBO data do not have position adjustment, league adjustment and park factor which are essential in calculating WAR. In this paper, using five statistics for both KBO and MLB qualified batters, we propose hitting ability index (HAI), an alternative sabermetric indices to represent batters' ability. Comparing HAI with WAR of MLB batters, we evaluate the validity of HAI and then applied HAI to 2015 KBO data in which HAI is analyzed statistically with respect to different teams, ages, and positions. Moreover, the linear relationship between KBO batter's HAI and their annual salary is discussed. Grouping 46 KBO batters based on confidence region of the regression model for annual salary, we also statistically investigate batter's annual salary in these groups with respect to several factors.