Sports Data Mining

by Robert P. Schumaker, Osama K. Solieman, Hsinchun Chen

Overview

Data mining is the process of extracting hidden patterns from data, and it’s commonly used in business, bioinformatics, counter-terrorism, and, increasingly, in professional sports. First popularized in Michael Lewis’ best-selling Moneyball: The Art of Winning An Unfair Game, it is has become an intrinsic part of all professional sports the world over, from baseball to cricket to soccer. While an industry has developed based on statistical analysis services for any given sport, or even for betting behavior analysis on these sports, no research-level book has considered the subject in any detail until now.

Sports Data Mining brings together in one place the state of the art as it concerns an international array of sports: baseball, football, basketball, soccer, greyhound racing are all covered, and the authors (including Hsinchun Chen, one of the most esteemed and well-known experts in data mining in the world) present the latest research, developments, software available, and applications for each sport. They even examine the hidden patterns in gaming and wagering, along with the most common systems for wager analysis.

Product Details

ISBN-13:	9781441967299
Publisher:	Springer US
Publication date:	09/30/2010
Series:	Integrated Series in Information Systems , #26
Edition description:	2010
Pages:	138
Product dimensions:	6.10(w) x 9.20(h) x 0.50(d)

About the Author

Dr. Robert Schumaker is an Assistant Professor in Information Systems at Iona College. Rob's overall research interests involve the uses of technology to acquire, deliver and make predictions in a variety of Business-related environments. These interests further branch into computer mediated communications, design science, human computer interfaces, machine learning algorithms, natural language processing, technology acceptance models and textual data mining. His recent research has focused on Sports Knowledge Management and Data Mining of relevant data from Sports-related databases and producing accurate predictions that can provide an edge to sports organizations and gamblers alike. Using the Moneyball style philosophy, this project analyzes the use of different machine learning techniques to predict outcomes of sporting events.

He has authored or co-authored many journal articles, including ACM Transactions on Information Systems, Decision Support Systems, IEEE Systems, Man and Cybernetics – Part A and Communications of the ACM.

Osama K. Solieman attended the University of Arizona graduating with a BS in Computer Science in 2003. In 2006, he received a MS in Management Information Systems where he was also the lead researcher on a database project for the Department of Electrical & Computer Engineering. Currently, he is an IT Consultant regularly working with Fortune 500 companies and traveling extensively around the world. He remains an avid sports fan and is active in his community.

Hsinchun Chen is McClelland Professor of Management Information Systems (MIS) at the Eller College of the University of Arizona and Andersen Consulting Professor of the Year (1999). He is the author of 15 books and more than 200 articles covering knowledge management, digital library, homeland security, Web computing, andbiomedical informatics in leading information technology publications. He serves on ten editorial boards, including: Journal of the American Society for Information Science and Technology, ACM Transactions on Information Systems, IEEE Transactions on Systems, Man, and Cybernetics, IEEE Transactions on Intelligent Transportation Systems, International Journal of Digital Library, and Decision Support Systems. He has served as a Scientific Advisor/Counselor of the National Library of Medicine (USA), Academia Sinica (Taiwan), and National Library of China (China). Dr. Chen founded The University of Arizona Artificial Intelligence Lab in 1990. The group is distinguished for its applied and high-impact AI research. Since 1990, Dr. Chen has received more than $20M in research funding from various government agencies and major corporations. He has been a PI of the NSF Digital Library Initiative Program and the NIH NLM’s Biomedical Informatics Program. His group has developed advanced medical digital library and data and text mining techniques for gene pathway and disease informatics analysis and visualization since 1995. Dr. Chen’s nanotechnology patent analysis works, funded by NSF, have been published in the Journal of Nanoparticle Research. His research findings were used in the President’s Council of Advisors in Science and Technology’s report on "The National Nanotechnology Initiative at Five Years: Assessment and Recommendations of the National Nanotechnology Advisory Panel." Dr. Chen’s work also has been recognized by major US corporations and been awarded numerous industry awards for his contribution to IT education and research, including: AT&T Foundation Award in Science and Engineering and SAP Award in Research/Applications. Dr. Chen has been heavily involved in fostering digital library, medical informatics, knowledge management, and intelligence informatics research and education in the US andinternationally. He has been a PI for more than 20 NSF and NIH research grants since 1990. Dr. Chen is conference chair of ACM/IEEE Joint Conference on Digital Libraries (JCDL) 2004 and has served as the conference general chair or international program committee chair for the past six International Conferences of Asian Digital Libraries (ICADL), 1998-2005. He has been instrumental in fostering the ICADL activities in Asia. Dr. Chen is the founder and also conference co-chair of the IEEE International Conference on Intelligence and Security Informatics (ISI), 2003-2006. The ISI conference has become the premiere meeting for international, national, and homeland security IT research. Dr. Chen is an IEEE fellow.

Table of Contents

1 Sports Data Mining: The Field 1

Chapter Overview 1

1 Definition 2

2 History 5

3 Societal Dimensions 8

4 The International Landscape 10

5 Criticisms 12

6 Questions for Discussion 13

2 Sports Data Mining Methodology 15

Chapter Overview 15

1 Scientific Foundation 16

2 Traditional Data Mining Applications 18

3 Deriving Knowledge 20

4 Questions for Discussion 21

3 Data Sources for Sports 23

Chapter Overview 23

1 Introduction 23

2 Professional Societies 24

2.1 The Society for American Baseball Research 24

2.2 Association for Professional Basketball Research 24

2.3 Professional Football Researchers Association 25

3 Sport-Related Associations 25

3.1 The International Association on Computer Science in Sport 25

3.2 The International Association for Sports Information 26

4 Special Interest Sources 26

4.1 Baseball 26

4.2 Basketball 26

4.3 Football 27

4.4 Cricket 27

4.5 Soccer 27

4.6 Multiple Sports 28

5 Conclusions 28

6 Questions for Discussion 28

4 Research in Sports Statistics 29

Chapter Overview 29

1 Introduction 29

2 Sports Statistics 29

2.1 History and Inherent Problems of Statistics in Sports 30

2.2 Bill James 31

2.3 Dean Oliver 32

3 Baseball Research 32

3.1 Building Blocks 33

3.2 Runs Created 33

3.3 Win Shares 35

3.4 Linear Weights and Total Player Rating 35

3.5 Pitching Measures 36

4 Basketball Research 37

4.1 Shot Zones 37

4.2 Player Efficiency Rating 38

4.3 Plus/Minus Rating 38

4.4 Measuring Player Contribution to Winning 39

4.5 Rating Clutch Performances 39

5 Football Research 40

5.1 Defense-Adjusted Value Over Average 40

5.2 Defense-Adjusted Points Above Replacement 41

5.3 Adjusted Line Yards 41

6 Emerging Research in Other Sports 41

6.1 NCAA Bowl Championship Series 42

6.2 NCAA Men's Basketball Tournament 42

6.3 Soccer 43

6.4 Cricket 43

6.5 Olympic Curling 44

7 Conclusions 44

8 Questions for Discussion 44

5 Tools and Systems for Sports Data Analysis 45

Chapter Overview 45

1 Introduction 45

2 Sports Data Mining Tools 46

2.1 Advanced Scout 46

2.2 Synergy Online 47

2.3 Sports Vis 47

2.4 Sports Data Hub 48

3 Scouting Tools 49

3.1 Digital Scout 49

3.2 Inside Edge 49

4 Sports Fraud Detection 50

4.1 Las Vegas Sports Consultants 52

4.2 Offshore Gaming 53

5 Conclusions 53

6 Questions for Discussion 53

6 Predictive Modeling for Sports and Gaming 55

Chapter Overview 55

1 Introduction 55

2 Statistical Simulations 56

2.1 Baseball 56

2.2 Basketball's BBall 57

2.3 Other Sporting Simulations 58

3 Machine Learning 58

3.1 Soccer 58

3.2 Greyhound and Thoroughbred Racing 59

3.3 Commercial Products 60

4 Conclusions 63

5 Questions for Discussion 63

7 Multimedia and Video Analysis for Sports 65

Chapter Overview 65

1 Introduction 65

2 Searchable Video 66

2.1 SoccerQ 67

2.2 Blinkx 68

2.3 Clipta 68

2.4 Sports VHL 69

2.5 Truveo 69

2.6 Bluefin Lab 69

3 Motion Analysis 69

4 Conclusions 70

5 Questions for Discussion 70

8 Web Sports Data Extraction and Visualization 71

Chapter Overview 71

1 Introduction 71

2 Web Data Sources 72

2.1 Baseball 72

2.2 Basketball 74

2.3 Cricket 77

2.4 Football 78

2.5 Hockey 81

2.6 Soccer 82

2.7 Other Sport Sources 83

3 Extracting Data 84

3.1 Programs 85

4 Conclusions 87

5 Questions for Discussion 87

9 Open Source Data Mining Tools for Sports 89

Chapter Overview 89

1 Introduction 89

2 WEKA 89

3 Rapidminer 91

4 Conclusions 92

5 Questions for Discussion 92

10 Greyhound Racing Using Neural Networks: A Case Study 93

Chapter Overview 93

1 Introduction 93

2 Setting Up the Experiments 94

3 Testing ID3 96

4 Testing the Backpropagation Neural Network 98

5 The Results 98

6 Conclusions 99

7 Questions for Discussion 100

11 Greyhound Racing Using Support Vector Machines: A Case Study 101

Chapter Overview 101

1 Introduction 101

2 Relevant Literature 102

3 Research Methodology 103

3.1 Data Acquisition 105

3.2 Support Vector Machines Algorithm 105

4 Results 106

5 Conclusions 108

6 Questions for Discussion 108

12 Betting and Gaming 109

Chapter Overview 109

1 Introduction 109

2 The Effects on Gambling on Sports 109

3 Sportsbooks and Offshore Betting 111

4 Arbitrage Methods 112

5 Cautions and Gambling Pitfalls 113

6 Conclusions 113

7 Questions for Discussion 114

13 Conclusions 115

Chapter Overview 115

1 Sports Data Mining Challenges 115

2 Sports Data Mining Audience 116

3 Future Directions 117

References 119

Index 127