This item is available under a Creative Commons License for non-commercial use only
Computer Sciences, Information Science
Driven by the increasing comprehensive data in sports datasets and data mining technique successfully used in different area, sports data mining technique emerges and enables us to find hidden knowledge to impact the sport industry. In many instances, predicting the outcomes of sporting events has always been a challenging and attractive work and is therefore drawing a wide concern to conduct research in this field. This project focuses on using machine learning algorithms to build a model for predicting the NBA game outcomes and the algorithms involve Simple Logistics Classifier, Artificial Neural Networks, SVM and Naïve Bayes. In order to complete a convincing result, data of 5 regular NBA seasons was collected for model training and data of 1 NBA regular season was used as scoring dataset. After processes of automated data collection and cloud techniques enabled data management, a data mart containing NBA statistics data is built. Then machine learning models mentioned above is trained and tested by consuming data in the data mart. After applying scoring dataset to evaluate the model accuracy, Simple Logistics Classifier finally yields the best result with an accuracy of 69.67%. The results obtained are compared to other methods from different source. It was found that results of this project are more persuasive since such a vast quantity of data was applied in this project. Meanwhile, it can be referenced for the future work.
Cao, C.: Sports data mining technology used in basketball outcome prediction. Masters Dissertation. Dublin Institute of Technology, 2012.