Discovering the Factors Influencing Professional Baseball Box Office using Machine Learning

In the past, the data analyses in professional baseball, i.e sabermetrics, focus on evaluation of players and organizing a team for winning more games because good players bring wins and winning brings business. However, winning might not be sufficient. The previous study about annual box office in Chinese Professional Baseball League shown that the franchise reputation and playing styles matter. In this paper, the factors influencing per game attendance in CPBL are further studied using machine learning techniques. As a result, we found that the game statistics have no influences to attendance. As long as the weather is during weekend, fans would attend the ball park to support the franchise highly address the local business.