Data Warehousing and Data Mining for Telecommunications (Artech House Computer Science Library)

Foreword  xiii......Page 13
Preface  xvii......Page 16
1  Everything’s up to date in Kansas City  1......Page 18
1.1  The current industry composition  3......Page 20
1.2  Why is telecommunications so BIG?  4......Page 21
1.3  Telecommunications: the major driving economic force of the 21st century  5......Page 22
1.4  Knowledge management enablement—the biggest factor of all  6......Page 23
1.5  The ultimate environment  7......Page 24
1.6  Future directions  8......Page 25
1.7  Telecommunications and technological innovation  9......Page 26
1.9  Customer intimacy—from “network is king” to “customer is king”  10......Page 27
1.10  Operational efficiency—being the low-cost provider of choice  11......Page 28
1.12  Conclusion  12......Page 29
2  Why warehousing and how to get started  13......Page 30
2.1  Background of data warehousing  14......Page 31
2.2  Data mining  18......Page 35
2.3  Why are these approaches so exceptionally valuable to telecommunications firms?  20......Page 37
2.4  Organizing the process  22......Page 39
3  The knowledge management view of business and warehousing  25......Page 41
3.1  The knowledge management revolution  26......Page 42
3.2  Efficiency optimization—optimize the silo or optimize the whole  32......Page 48
3.3  The corporate global warehouse model  38......Page 54
3.4  Overall strategy for development (one piece at a time, fitting into the overall architecture)  45......Page 61
4  The telecommunications value chain  51......Page 67
4.2  Steps in the process of deriving a business’ value chain  52......Page 68
4.3  Telecommunications functions and systems  53......Page 69
4.4  Organizational structure and the value chain  63......Page 79
4.5  Allocating the business units to the value chain and the knowledge management process  66......Page 82
5  Building the warehouse—one step at a time  79......Page 95
5.1  Challenges to infrastructure design  80......Page 96
5.2  The functional components of a warehouse environment  84......Page 100
5.3  The step-by-step, cost-justified approach  89......Page 105
5.4  How do you build a warehouse?  92......Page 108
6  Value propositions in telecommunications  95......Page 110
6.1  Mining tools and value delivery  96......Page 111
6.2  Value propositions by functional area  98......Page 113
6.3  Conclusions  105......Page 120
7  Simple sales analysis: an introduction to operational monitoring using Microsoft Query  107......Page 122
7.1  Operational efficiency—an overview  109......Page 124
7.2  Sales monitoring and control  110......Page 125
7.4  Using Microsoft Query and Excel to do sales tracking  111......Page 126
7.6  Alternative methods of accessing data  115......Page 130
8  Sales and product management: advanced operational monitoring using COGNOS PowerPlay  117......Page 132
8.1  Monitoring complex business organizations  118......Page 133
8.2  Exploring sales and product performance  121......Page 136
8.3  Additional PowerPlay features  124......Page 139
8.4  Summary  127......Page 142
9  Customer intimacy: an introduction using SPSS  129......Page 143
9.1  An introduction to analytical mining  130......Page 144
9.2  Statistical analysis—options and objectives  131......Page 145
9.3  Descriptive approaches  133......Page 147
9.4  Inferential approaches—regression analysis  137......Page 151
9.5  Conclusions on statistical analysis  140......Page 154
10  Predicting customer behavior: an introduction to neural networks  143......Page 156
10.1  Unraveling complex situations  144......Page 157
10.3  Step-by-step use of a neural network  145......Page 158
10.5  Conclusion on neural networks  152......Page 165
11  Engineering and competitive analysis support: an introduction to geographical systems and MapInfo  155......Page 167
11.1  An introduction to MapInfo Professional  156......Page 168
11.2  Using geographical information to solve telecommunications problems  158......Page 170
11.3  Cellsite analysis with MapInfo Professional  159......Page 171
11.4  Market analysis capabilities  162......Page 174
11.5  Viewing a local market in greater detail  164......Page 176
11.6  Accessibility to fiber analysis  165......Page 177
11.7  Working with the underlying database  167......Page 179
11.8  Conclusion  168......Page 180
Appendix A: Real world warehousing: France Telecom and STATlab tools  169......Page 181
A data warehouse solution with STATlab tools  170......Page 182
The corporate information system of France Telecom  171......Page 183
Cases of telecommunications data exploration  172......Page 184
Churn customer data and decision making  187......Page 199
Fraud detection  196......Page 208
Architecture and Technical Specifications  200......Page 212
Enduser tools  201......Page 213
Conclusion  209......Page 221
Appendix B: The business case for business intelligence  211......Page 223
B.1  Our credentials: background of Holistic Systems/Seagate Holos  212......Page 224
B.2  Technology alone is the wrong emphasis  213......Page 225
B.3  Focusing on the business is the right emphasis  214......Page 226
B.4  What distinguishes enterprise business intelligence?  215......Page 227
B.5  Talking about the technology  218......Page 230
B.6  Individual technology components of enterprise business intelligence systems  219......Page 231
B.7  A closer look at OLAP  220......Page 232
B.8  Open OLAP—a better approach  222......Page 234
B.9  Seagate Holos’ architecture  224......Page 236
B.10  Thin client with agents, neural nets, and more  225......Page 237
B.12  BT uses Seagate Holos for project tracking  229......Page 241
B.13  Ameritech uses Seagate Holos for sales reporting  235......Page 247
C.1  Extend your analysis  239......Page 250
C.2  Use a comprehensive solution  240......Page 251
C.4  Company information  241......Page 252
C.5  SPSS offices  242......Page 253
Appendix D: The DecisionWORKS suite from Advanced Software Applications  245......Page 256
D.1  ModelMAX: the new standard for predictive modeling  246......Page 257
D.2  dbPROFILE: a breakthrough for custom clustering and data visualization  249......Page 260
D.3  For more information  250......Page 261
Data management terms  251......Page 262
Data analysis terms  254......Page 265
Selected bibliography  257......Page 268
About the author  261......Page 272
Index  263......Page 273