Microsoft Data Mining  Integrated Business Intelligence for e-Commerce and Knowledge Management
作者: Barry De Ville
日期: April 20, 2001
ISBN: 1555582427
页数: 320
语言: English
出版社: Digital Press

Microsoft Data Mining approaches data mining from the particular perspective of IT professionals using Microsoft data management technologies. The author explains the new data mining capabilities in Microsoft's SQL Server 2000 database, Commerce Server, and other products, details the Microsoft OLE DB for Data Mining standard, and gives readers best practices for using all of them. The book bridges the previously specialized field of data mining with the new technologies and methods that are quickly making it an important mainstream tool for companies of all sizes.
Data mining refers to a set of technologies and techniques by which IT professionals search large databases of information (such as those contained by SQL Server) for patterns and trends. Traditionally important in finance, telecommunication, and other information-intensive fields, data mining increasingly helps companies better understand and serve their customers by revealing buying patterns and related interests. It is becoming a foundation for e-commerce and knowledge management.
Unique book on a hot data management topic
Part of Digital Press's SQL Server and data mining clusters
Author is an expert on both traditional and Microsoft data mining technologies
From the Publisher
Data mining refers to a set of technologies and techniques by which IT professionals search large databases of information (such as those contained by SQL Server) for patterns and trends. Traditionally important in finance, telecommunication, and other information-intensive fields, data mining increasingly helps companies better understand and serve their customers by revealing buying patterns and related interests. It is becoming a foundation for e-commerce and knowledge management.

Contents
Foreword xi
Preface xiii
Acknowledgments xix
1 Introduction to Data Mining 1
1.1 Something old, something new 3
1.2 Microsoft’s approach to developing the right set of tools 7
1.3 Benefits of data mining 10
1.4 Microsoft’s entry into data mining 18
1.5 Concept of operations 19
2 The Data Mining Process 23
2.1 Best practices in knowledge discovery in databases 24
2.2 The scientific method and the paradigms that come with it 25
2.3 How to develop your paradigm 30
2.4 The data mining process methodology 37
2.5 Business understanding 39
2.6 Data understanding 41
2.7 Data preparation 44
2.8 Modeling 45
2.9 Evaluation 49
2.10 Deployment 51
2.11 Performance measurement 54
2.12 Collaborative data mining: the confluence of data mining
and knowledge management 55
3 Data Mining Tools and Techniques 59
3.1 Microsoft’s entry into data mining 60
3.2 The Microsoft data mining perspective 60
viii Contents
3.3 Data mining and exploration (DMX) projects 64
3.4 OLE DB for data mining architecture 65
3.5 The Microsoft data warehousing framework and alliance 71
3.6 Data mining tasks supported by SQL Server 2000
Analysis Services 72
3.7 Other elements of the Microsoft data mining strategy 86
4 Managing the Data Mining Project 93
4.1 The mining mart 94
4.2 Unit of analysis 95
4.3 Defining the level of aggregation 97
4.4 Defining metadata 98
4.5 Calculations 99
4.6 Standardized values 102
4.7 Transformations for discrete values 103
4.8 Aggregates 103
4.9 Enrichments 111
4.10 Example process (target marketing) 112
4.11 The data mart 115
5 Modeling Data 117
5.1 The database 118
5.2 Problem scenario 118
5.3 Setting up analysis services 120
5.4 Defining the OLAP cube 124
5.5 Adding to the dimensional representation 132
5.6 Building the analysis view for data mining 135
5.7 Setting up the data mining analysis 137
5.8 Predictive modeling (classification) tasks 139
5.9 Creating the mining model 141
5.10 The tree navigator 147
5.11 Clustering (creating segments) with cluster analysis 151
5.12 Confirming the model through validation 158
5.13 Summary 159
6 Deploying the Results 163
6.1 Deployments for predictive tasks (classification) 164
6.2 Lift charts 172
6.3 Backing up and restoring databases 175
7 The Discovery and Delivery of Knowledge for Effective
Enterprise Outcomes: Knowledge Management 177
7.1 The role of implicit and explicit knowledge 179
7.2 A primer on knowledge management 180
7.3 The Microsoft technology-enabling framework 199
7.4 Summary 208
Appendix A: Glossary 213
Appendix B: References 219
Appendix C: Web Sites 223
Appendix D: Data Mining and Knowledge Discovery
Data Sets in the Public Domain 229
Appendix E: Microsoft Solution Providers 255
Appendix F: Summary of Knowledge Management
Case Studies and Web Locations 289
Index