Data Analysis Using SQL and Excel (eBook)

GORDON S. LINOFF has been working with databases for more decades than he cares to admit. He starting learning about SQL by memorizing the SQL 92 standard while leading a development team (at the now-defunct Thinking Machines Corporation) writing the first high-performance database focused on the complex queries needed for decision support. After that endeavor, Gordon co-founded Data Miners in 1998, a consulting practice devoted to data mining, analytics, and big data. A constant theme in his work is data--and often data in relational databases. His SQL skills have only gotten stronger over the years. In 2014, he was the top contributor to Stack Overflow, the leading question-and-answer-site for technical questions. His other books include the bestselling Data Mining Techniques, Third Edition; Mastering Data Mining; and Mining the Web--which focus on data mining and analysis. This book follows on the popularity of the first edition, with a practical focus on how to actually get and interpret results.

Foreword xxxiii

Introduction xxxvii

Chapter 1 A Data Miner Looks at SQL 1

Chapter 2 What's in a Table? Getting Started with Data Exploration 49

Chapter 3 How Different Is Different? 97

Chapter 4 Where Is It All Happening? Location, Location, Location 145

Chapter 5 It's a Matter of Time 197

Chapter 6 How Long Will Customers Last? Survival Analysis to Understand Customers and Their Value 255

Chapter 7 Factors Affecting Survival: The What and Why of Customer Tenure 315

Chapter 8 Customer Purchases and Other Repeated Events 367

Chapter 9 What's in a Shopping Cart? Market Basket Analysis 421

Chapter 10 Association Rules and Beyond 465

Chapter 11 Data Mining Models in SQL 507

Chapter 12 The Best-Fit Line: Linear Regression Models 561

Chapter 13 Building Customer Signatures for Further Analysis 609

Chapter 14 Performance Is the Issue: Using SQL Effectively 655

Appendix Equivalent Constructs Among Databases 703

Index 731