[1]曾磐,朱安民.基于支持向量机的NBA季后赛预测方法[J].深圳大学学报理工版,2016,33(1):62-71.[doi:10.3724/SP.J.1249.2016.01062]
 Zeng Pan and Zhu Anmin.A SVM-based model for NBA playoffs prediction[J].Journal of Shenzhen University Science and Engineering,2016,33(1):62-71.[doi:10.3724/SP.J.1249.2016.01062]
点击复制

基于支持向量机的NBA季后赛预测方法()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第33卷
期数:
2016年第1期
页码:
62-71
栏目:
电子与信息科学
出版日期:
2016-01-20

文章信息/Info

Title:
A SVM-based model for NBA playoffs prediction
文章编号:
201601009
作者:
曾磐朱安民
深圳大学计算机与软件学院,广东深圳 518060
Author(s):
Zeng Pan and Zhu Anmin
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, Guangdong Province, P.R.China
关键词:
计算机感知NBA季后赛因子分析支持向量机不平衡数据欠采样过采样
Keywords:
computer perception NBA playoffs factor analysis support vector machine unbalanced data undersampling oversampling
分类号:
TP 391
DOI:
10.3724/SP.J.1249.2016.01062
文献标志码:
A
摘要:
通过对参加NBA赛事的每支球队在常规赛阶段的数据统计,整合出球队常规赛综合得分、球员常规赛综合得分、主教练水平及主客场因素4项指标作为一支球队的综合实力体现,构建训练样本,使用适合小样本数据的基于结构风险最小化的支持向量机(support vector machine, SVM)来训练一个预测模型,并预测NBA季后赛每场比赛的胜负.通过结合欠采样和过采样技术消除训练样本中的不平衡数据,更好地发挥SVM的学习能力.实验表明,所提方法具有较好的预测效果.
Abstract:
We use four statistics data from the NBA regular season including team comprehensive score, player comprehensive score, chief coach capability, and the impact of home and away games as the indicators to build up training samples. Then, we construct a prediction model based on a support vector machine (SVM), which is suitable for solving the problem of a small sample size and has the theoretical basis of structural risk minimization. We combine the technique of undersampling and oversampling to remove the unbalanced data in training datasets, thus improving the leaning ability of SVM. Experimental results show that the proposed method has a relatively preferable performance.

参考文献/References:

[1] Melnick M J. Relation between team assists and win-loss record in the National Basketball Association[J]. Percept Mot Skills,2001, 92(2): 595-602.
[2] 靳勇.2005—2006赛季NBA总决赛制胜因素探析[J].哈尔滨体育学院学报,2006,24(6):118-119.
Jin Yong. The winning factors of the finals of 2005—2006 NBA season[J]. Harbin Sports Institute Proceedings, 2006, 24(6): 118-602.(in Chinese)
[3] 邱胜,段重阳,陈征.NBA季后赛成绩分析及预测:Logistic和Bayes模型[J].统计教育,2010(10):46-51.
Qiu Sheng, Duan Chongyang, Chen Zheng. Analysis and forecast of playoff teams promotions with Logistic and Bayes model[J]. Statistical Education, 2010(10): 46-51.(in Chinese)
[4] Chatterjee S, Campbell M R, Wiseman F. Take that Jam! An analysis of winning percentage for NBA teams[J]. Managerial and Decision Economics, 1994, 15(5): 521-535.
[5] Ni Jianjun, Zhang Chuanbiao, Ren Li, et al. Abrupt event monitoring for water environment system based on KPCA and SVM[J]. IEEE Transactions on Instrumentation and Measurement, 2012, 61(4): 980-989.
[6] Torheim T, Malinen E, Kvaal K, et al. Classification of dynamic contrast enhanced MR images of cervical cancers using texture analysis and support vector machines[J]. IEEE Transactions on Medical Imaging, 2014, 33(8): 1648-1656.
[7] Sports Reference LLC. Glossary: poss, GmSc[DB/OL].[2015-09-11]. http://www.basketball-reference.com/about/glossary.html.
[8] 童智靖.不均衡数据下基于SVM的分类算法研究与应用[D].哈尔滨:哈尔滨工程大学,2011.
Tong Zhijing. Unbalanced data classification algorithm based on SVM for research and application[D]. Harbin: Harbin Engineering University, 2011.(in Chinese)
[9] Bhanu P K N, Ramakrisbnan A G, Suresh S, et al. Fetal lung maturity analysis using ultrasound image features[C]// IEEE Transactions on Information Technology in Biomedicine.[S.l.]:IEEE, 2002, 6(1): 38-45.
[10] Alpaydin E.机器学习导论[M].2版.范明,昝红英,牛常勇,译.北京: 机械工业出版社,2009:1-2,142.
Alpaydin E. Introduction to machine learning[M]. 2nd ed. Fan Ming, Zan Hongying, Niu Changyong, trans. Beijing: China Machine Press, 2009: 1-2, 142.(in Chinese)
[11] Wang F, He K, Liu Y, et al. Research on the selection of kernel function in SVM based facial expression recognition[C]// The 8th IEEE Conference on Industrial Electronics and Applications (ICIEA). Melbourne, Australia: IEEE, 2013: 1404-1408.
[12] Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16(1): 321-357.
[13] Zhu Anmin, Yi Xin. The comparisons of four methods for financial forecast[C]// Proceeding of the IEEE International Conference on Automation and Logistics. Zhengzhou: IEEE, 2012: 45-50.

相似文献/References:

[1]文振焜,陈斌,吴惠思.基于自适应哈希算法的直播视频篡改检测[J].深圳大学学报理工版,2017,34(2):165.
 Wen Zhenkun,Chen Bin,and Wu Husi. Tamper detection based on adaptive hashing algorithm for live video streaming[J].Journal of Shenzhen University Science and Engineering,2017,34(1):165.
[2]明勇,张文斌,黄哲学,等.基于RFM购买树的客户分群[J].深圳大学学报理工版,2017,34(3):306.[doi:10.3724/SP.J.1249.2017.03306]
 Ming Yong,Zhang Wenbin,Huang Zhexue,et al.Customer segmentation based on RFM purchase tree[J].Journal of Shenzhen University Science and Engineering,2017,34(1):306.[doi:10.3724/SP.J.1249.2017.03306]

备注/Memo

备注/Memo:
Received:2015-10-03;Accepted:2015-12-10
Foundation:National Natural Science Foundation of China(61273354)
Corresponding author:Professor Zhu Anmin. E-mail: azhu@szu.edu.cn
Citation:Zeng Pan, Zhu Anmin. A SVM-based model for NBA playoffs prediction[J]. Journal of Shenzhen University Science and Engineering, 2016, 33(1): 62-71.(in Chinese)
基金项目:国家自然科学基金资助项目(61273354)
作者简介:曾磐(1992—),男,深圳大学硕士研究生.研究方向:数据挖掘.E-mail:q64545@sina.com
引文:曾磐,朱安民.基于支持向量机的NBA季后赛预测方法[J]. 深圳大学学报理工版,2016,33(1):62-71.
更新日期/Last Update: 2016-01-14