Predicting college basketball match outcomes using machine learning techniques: some results and lessons learned
This work addresses the problem of sports outcome prediction for analysts and bettors, but it is incremental as it builds on existing statistical approaches.
The paper tackled predicting college basketball match outcomes by evaluating various machine learning classification paradigms, finding that feature attributes are more important than models and that there is an upper limit to predictive quality.
Most existing work on predicting NCAAB matches has been developed in a statistical context. Trusting the capabilities of ML techniques, particularly classification learners, to uncover the importance of features and learn their relationships, we evaluated a number of different paradigms on this task. In this paper, we summarize our work, pointing out that attributes seem to be more important than models, and that there seems to be an upper limit to predictive quality.