Abstract In many real-life sports games, spectators are interested in predicting the outcomes and watching the games to verify their predictions. Traditional approaches include subjective prediction, objective prediction, and simple statistical methods. However, these approaches may not be too reliable in many situations. In this paper, we present a sports data mining approach, which helps discover interesting knowledge and predict outcomes of sports games such as college football. Our approach makes predictions based on a combination of four different measures on the historical results of the games. Evaluation results on real-life college football data shows that our approach leads to relatively high accuracy in result prediction.
Paper
Full text
Sports Data Mining: Predicting Results for the College Football Games
Semantic Scholar · Computer Science · 2014
Abstract
Abstract In many real-life sports games, spectators are interested in predicting the outcomes and watching the games to verify their predictions. Traditional approaches include subjective prediction, objective prediction, and simple statistical methods. However, these approaches may not be too reliable in many situations. In this paper, we present a sports data mining approach, which helps discover interesting knowledge and predict outcomes of sports games such as college football. Our approach makes predictions based on a combination of four different measures on the historical results of the games. Evaluation results on real-life college football data shows that our approach leads to relatively high accuracy in result prediction.