A hybrid ensemble learning framework for basketball outcomes prediction

Abstract Basketball outcomes prediction is a vital technique for prospective player arrangement, injury avoidance, telecast right pricing, etc., which requires a understanding of the skill, luck, and other exterior factors of both teams. This paper presents a hybrid ensemble learning framework for basketball outcomes prediction by learning the recent status of the teams. To achieve this, we first design a new weighted combination feature for a future game by considering the latest status of the home team and the visiting team. Then, we present a hybrid ensemble framework equipped with bagging strategy and random subspace method to enlarge the diversity of the samples by learning a series of support vector machines. Finally, we develop a voting mechanism to predict the basketball outcomes. Extensive experiments have demonstrated the outperformance of our framework.

[1]  P. Dorian Owen,et al.  Measurement of competitive balance and uncertainty of outcome , 2014 .

[2]  Andreas Stenling,et al.  Psychosocial Factors and Sport Injuries: Meta-analyses for Prediction and Prevention , 2017, Sports Medicine.

[3]  Jean-Philippe Vert,et al.  A bagging SVM to learn from positive and unlabeled examples , 2010, Pattern Recognit. Lett..

[4]  Peter Bühlmann,et al.  Bagging, Boosting and Ensemble Methods , 2012 .

[5]  Hyeonsang Eom,et al.  A compound framework for sports results prediction: A football case study , 2008, Knowl. Based Syst..

[6]  Shiliang Sun,et al.  Subspace ensembles for classification , 2007 .

[7]  Jarrod Trevathan,et al.  Artificial Intelligence in Sports Prediction , 2008, Fifth International Conference on Information Technology: New Generations (itng 2008).

[8]  Duncan J. Watts,et al.  Exploring Limits to Prediction in Complex Social Systems , 2016, WWW.

[9]  Dragan Miljkovic,et al.  The use of data mining for basketball matches outcomes prediction , 2010, IEEE 8th International Symposium on Intelligent Systems and Informatics.

[10]  Renato Assunção,et al.  Luck is Hard to Beat: The Difficulty of Sports Prediction , 2017, KDD.

[11]  Joachim Gudmundsson,et al.  Spatio-Temporal Analysis of Team Sports , 2016, ACM Comput. Surv..

[12]  Benjamin H. Brinkmann,et al.  SVM-Based System for Prediction of Epileptic Seizures From iEEG Signal , 2017, IEEE Transactions on Biomedical Engineering.

[13]  Genny Tortora,et al.  A data mining based system supporting tactical decisions , 2002, SEKE '02.

[14]  Peijun Du,et al.  Random Subspace Ensembles for Hyperspectral Image Classification With Extended Morphological Attribute Profiles , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Jerzy Stefanowski,et al.  Neighbourhood sampling in bagging for imbalanced data , 2015, Neurocomputing.

[16]  Erik Štrumbelj,et al.  Simulating a basketball match with a homogeneous Markov model and forecasting the outcome , 2012 .

[17]  Rodney Fort,et al.  “Competitive Balance in Sports Leagues: An Introduction” , 2003 .

[18]  Rui Yao,et al.  A novel intelligent diagnosis method using optimal LS-SVM with improved PSO algorithm , 2017, Soft Computing.

[19]  Gilles Louppe,et al.  Ensembles on Random Patches , 2012, ECML/PKDD.

[20]  John A. Fortunato,et al.  Sports Leagues’ Game Exposure Policies: Economic and Legal Complexities , 2018 .

[21]  Jason Ferris,et al.  Alcohol Advertising in Sport and Non-Sport TV in Australia, during Children’s Viewing Times , 2015, PloS one.

[22]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[23]  Francisco J. R. Ruiz,et al.  A generative model for predicting outcomes in college basketball , 2015 .

[24]  Shuang Wang,et al.  A robust semi-supervised SVM via ensemble learning , 2018, Appl. Soft Comput..