발간년도 : [2020]
| 논문정보 |
|
| 논문명(한글) |
[Vol.15, No.4] High-School Baseball Pitcher’s ERA(Earned Run Average) Prediction Using Multi-Variable Linear Regression Analysis Method |
|
| 논문투고자 |
Young-Hwan Oh |
|
| 논문내용 |
Recently, studies on artificial intelligence has been actively conducted, and scholars and researchers are constantly trying to create artificial intelligence beyond humans. Machine learning uses mathematics' logical algorithms to learn, analyze and predict various data. It assists decision making based on this analysis. The goal is not to directly write algorithms optimized for software or programs, but to create execution capabilities by letting IT devices or electronic devices themselves learn using large-scale big data and learning algorithms. Linear regression is a regression analysis method that models the linear correlation between one or more independent variables(x) and a dependent variable(y). Generally, a linear regression model is established using a least squares method. Multiple linear regression analysis targets regression models with two or more independent variables. Simple regression analysis can bring bias by estimating with only one independent variable. A baseball player's pitching ability depends on his speed, ball and concentration. In particular, among pitchers' stats, WHIP, H/9(Hits Runs Allowed Per 9 Innings Pitched) and K/9(Strikeout Per 9 Innings Pitched) are important measures of pitching. In this paper, the ERA(Earned Run Average) is predicted using the pitcher's WHIP, H/9 and K/9 as training data. We can predict whether a specific pitcher will be nominated for a professional baseball player or not. |
|
| 첨부논문 |
|
|
|
|
|
자료실 > 논문지 
