Please use this identifier to cite or link to this item:
|Title:||Machine Learning Approaches to Predict Basketball Outcomes|
|Keywords:||Machine Learning;Sports;Support Vector Machine|
|Abstract:||Sports prediction has always been a spellbinding research area for sports fans to know more about their favorite team and players, for teams and players to enhance their performance, for team managers and coaches to make strategies of the game and for a growing number of gamblers for making the predictions and betting on those predictions. Nowadays, companies are spending more effort in machine learning to predict the sports outcomes. The drastic increase in demand for sports advice, the presence of abundant data in sports and rapid growth of advanced technologies such as machine learning attracted a number of researchers for sports prediction. Support Vector Machines (SVMs) are powerful techniques that handle classification problems effectively and efficiently. However, SVM models lack in rule generation. So, this examination leads towards the development of Hybrid Fuzzy-SVM model (HFSVM) by integrating fuzzy approach and SVM technique for prediction of the basketball game outcomes that help the coaches, teams, and players to enhance their performance. The HFSVM model combines the advantage of both SVM technique and fuzzy approach, which is a unique strength of SVM and rule generation ability of fuzzy approach using fuzzy membership functions. In the proposed work the developed HFSVM model is applied to the data of 800 NBA games from 2015-2016 regular season to predict basketball game outcome. The basketball game is becoming more and more popular due to its high scoring and fast paced nature. Also, the HFSVM model is compared with SVM model and the empirical results showed that the HFSVM model not only provides better results than SVM model but also provides relatively satisfactory prediction accuracy. Therefore, promising results can be obtained using HFSVM model when analyzing the outcomes of basketball competitions.|
|Description:||Master of Engineering -CSE|
|Appears in Collections:||Masters Theses@CSED|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.