Business intelligence : data mining and optimization for decision making

Business intelligence is a broad category of applications and technologies for gathering, providing access to, and analyzing data for the purpose of helping enterprise users make better business decisions. The term implies having a comprehensive knowledge of all factors that affect a business, such as customers, competitors, business partners, economic environment, and internal operations, therefore enabling optimal decisions to be made.

Business Intelligence provides readers with an introduction and practical guide to the mathematical models and analysis methodologies vital to business intelligence.

This book:

Combines detailed coverage with a practical guide to the mathematical models and analysis methodologies of business intelligence. Covers all the hot topics such as data warehousing, data mining and its applications, machine learning, classification, supply optimization models, decision support systems, and analytical methods for performance evaluation. Is made accessible to readers through the careful definition and introduction of each concept, followed by the extensive use of examples and numerous real-life case studies. Explains how to utilise mathematical models and analysis models to make effective and good quality business decisions.

This book is aimed at postgraduate students following data analysis and data mining courses.

Researchers looking for a systematic and broad coverage of topics in operations research and mathematical models for decision-making will find this an invaluable guide.

Author Notes

Carlo Vercellis - School of Management, Politecnico di Milano, Italy

As well as teaching courses in Operations Research and Business Intelligence, Professor Vercellis is director of the research group MOLD (Mathematical Modeling, Optimization, Learning from Data). He has written four book in Italian, contributed to numerous other books, and has had many papers published in a variety of international journals.

Preface	p. xiii
I Components of the decision-making process	p. 1
1 Business intelligence	p. 3
1.1 Effective and timely decisions	p. 3
1.2 Data, information and knowledge	p. 6
1.3 The role of mathematical models	p. 8
1.4 Business intelligence architectures	p. 9
1.4.1 Cycle of a business intelligence analysis	p. 11
1.4.2 Enabling factors in business intelligence projects	p. 13
1.4.3 Development of a business intelligence system	p. 14
1.5 Ethics and business intelligence	p. 17
1.6 Notes and readings	p. 18
2 Decision support systems	p. 21
2.1 Definition of system	p. 21
2.2 Representation of the decision-making process	p. 23
2.2.1 Rationality and problem solving	p. 24
2.2.2 The decision-making process	p. 25
2.2.3 Types of decisions	p. 29
2.2.4 Approaches to the decision-making process	p. 33
2.3 Evolution of information systems	p. 35
2.4 Definition of decision support system	p. 36
2.5 Development of a decision support system	p. 40
2.6 Notes and readings	p. 43
3 Data warehousing	p. 45
3.1 Definition of data warehouse	p. 45
3.1.1 Data marts	p. 49
3.1.2 Data quality	p. 50
3.2 Data warehouse architecture	p. 51
3.2.1 ETL tools	p. 53
3.2.2 Metadata	p. 54
3.3 Cubes and multidimensional analysis	p. 55
3.3.1 Hierarchies of concepts and OLAP operations	p. 60
3.3.2 Materialization of cubes of data	p. 61
3.4 Notes and readings	p. 62
II Mathematical models and methods	p. 63
4 Mathematical models for decision making	p. 65
4.1 Structure of mathematical models	p. 65
4.2 Development of a model	p. 67
4.3 Classes of models	p. 70
4.4 Notes and readings	p. 75
5 Data mining	p. 77
5.1 Definition of data mining	p. 77
5.1.1 Models and methods for data mining	p. 79
5.1.2 Data mining, classical statistics and OLAP	p. 80
5.1.3 Applications of data mining	p. 81
5.2 Representation of input data	p. 82
5.3 Data mining process	p. 84
5.4 Analysis methodologies	p. 90
5.5 Notes and readings	p. 94
6 Data preparation	p. 95
6.1 Data validation	p. 95
6.1.1 Incomplete data	p. 96
6.1.2 Data affected by noise	p. 97
6.2 Data transformation	p. 99
6.2.1 Standardization	p. 99
6.2.2 Feature extraction	p. 100
6.3 Data reduction	p. 100
6.3.1 Sampling	p. 101
6.3.2 Feature selection	p. 102
6.3.3 Principal component analysis	p. 104
6.3.4 Data discretization	p. 109
7 Data exploration	p. 113
7.1 Univariate analysis	p. 113
7.1.1 Graphical analysis of categorical attributes	p. 114
7.1.2 Graphical analysis of numerical attributes	p. 116
7.1.3 Measures of central tendency for numerical attributes	p. 118
7.1.4 Measures of dispersion for numerical attributes	p. 121
7.1.5 Measures of relative location for numerical attributes	p. 126
7.1.6 Identification of outliers for numerical attributes	p. 127
7.1.7 Measures of heterogeneity for categorical attributes	p. 129
7.1.8 Analysis of the empirical density	p. 130
7.1.9 Summary statistics	p. 135
7.2 Bivariate analysis	p. 136
7.2.1 Graphical analysis	p. 136
7.2.2 Measures of correlation for numerical attributes	p. 142
7.2.3 Contingency tables for categorical attributes	p. 145
7.3 Multivariate analysis	p. 147
7.3.1 Graphical analysis	p. 147
7.3.2 Measures of correlation for numerical attributes	p. 149
7.4 Notes and readings	p. 152
8 Regression	p. 153
8.1 Structure of regression models	p. 153
8.2 Simple linear regression	p. 156
8.2.1 Calculating the regression line	p. 158
8.3 Multiple linear regression	p. 161
8.3.1 Calculating the regression coefficients	p. 162
8.3.2 Assumptions on the residuals	p. 163
8.3.3 Treatment of categorical predictive attributes	p. 166
8.3.4 Ridge regression	p. 167
8.3.5 Generalized linear regression	p. 168
8.4 Validation of regression models	p. 168
8.4.1 Normality and independence of the residuals	p. 169
8.4.2 Significance of the coefficients	p. 172
8.4.3 Analysis of variance	p. 174
8.4.4 Coefficient of determination	p. 175
8.4.5 Coefficient of linear correlation	p. 176
8.4.6 Multicollinearity of the independent variables	p. 177
8.4.7 Confidence and prediction limits	p. 178
8.5 Selection of predictive variables	p. 179
8.5.1 Example of development of a regression model	p. 180
8.6 Notes and readings	p. 185
9 Time series	p. 187
9.1 Definition of time series	p. 187
9.1.1 Index numbers	p. 190
9.2 Evaluating time series models	p. 192
9.2.1 Distortion measures	p. 192
9.2.2 Dispersion measures	p. 193
9.2.3 Tracking signal	p. 194
9.3 Analysis of the components of time series	p. 195
9.3.1 Moving average	p. 196
9.3.2 Decomposition of a time series	p. 198
9.4 Exponential smoothing models	p. 203
9.4.1 Simple exponential smoothing	p. 203
9.4.2 Exponential smoothing with trend adjustment	p. 204
9.4.3 Exponential smoothing with trend and seasonality	p. 206
9.4.4 Simple adaptive exponential smoothing	p. 207
9.4.5 Exponential smoothing with damped trend	p. 208
9.4.6 Initial values for exponential smoothing models	p. 209
9.4.7 Removal of trend and seasonality	p. 209
9.5 Autoregressive models	p. 210
9.5.1 Moving average models	p. 212
9.5.2 Autoregressive moving average models	p. 212
9.5.3 Autoregressive integrated moving average models	p. 212
9.5.4 Identification of autoregressive models	p. 213
9.6 Combination of predictive models	p. 216
9.7 The forecasting process	p. 217
9.7.1 Characteristics of the forecasting process	p. 217
9.7.2 Selection of a forecasting method	p. 219
9.8 Notes and readings	p. 219
10 Classification	p. 221
10.1 Classification problems	p. 221
10.1.1 Taxonomy of classification models	p. 224
10.2 Evaluation of classification models	p. 226
10.2.1 Holdout method	p. 228
10.2.2 Repeated random sampling	p. 228
10.2.3 Cross-validation	p. 229
10.2.4 Confusion matrices	p. 230
10.2.5 ROC curve charts	p. 233
10.2.6 Cumulative gain and lift charts	p. 234
10.3 Classification trees	p. 236
10.3.1 Splitting rules	p. 240
10.3.2 Univariate splitting criteria	p. 243
10.3.3 Example of development of a classification tree	p. 246
10.3.4 Stopping criteria and pruning rules	p. 250
10.4 Bayesian methods	p. 251
10.4.1 Naive Bayesian classifiers	p. 252
10.4.2 Example of naive Bayes classifier	p. 253
10.4.3 Bayesian networks	p. 256
10.5 Logistic regression	p. 257
10.6 Neural networks	p. 259
10.6.1 The Rosenblatt perceptron	p. 259
10.6.2 Multi-level feed-forward networks	p. 260
10.7 Support vector machines	p. 262
10.7.1 Structural risk minimization	p. 262
10.7.2 Maximal margin hyperplane for linear separation	p. 266
10.7.3 Nonlinear separation	p. 270
10.8 Notes and readings	p. 275
11 Association rules	p. 277
11.1 Motivation and structure of association rules	p. 277
11.2 Single-dimension association rules	p. 281
11.3 Apriori algorithm	p. 284
11.3.1 Generation of frequent itemsets	p. 284
11.3.2 Generation of strong rules	p. 285
11.4 General Association rules	p. 288
11.5 Notes and readings	p. 290
12 Clustering	p. 293
12.1 Clustering methods	p. 293
12.1.1 Taxonomy of clustering methods	p. 294
12.1.2 Affinity measures	p. 296
12.2 Partition methods	p. 302
12.2.1 K-means algorithm	p. 302
12.2.2 K-medoids algorithm	p. 305
12.3 Hierarchical methods	p. 307
12.3.1 Agglomerative hierarchical methods	p. 308
12.3.2 Divisive hierarchical methods	p. 310
12.4 Evaluation of clustering models	p. 312
12.5 Notes and readings	p. 315
III Business intelligence applications	p. 317
13 Marketing models	p. 319
13.1 Relational marketing	p. 320
13.1.1 Motivations and objectives	p. 320
13.1.2 An environment for relational marketing analysis	p. 327
13.1.3 Lifetime value	p. 329
13.1.4 The effect of latency in predictive models	p. 332
13.1.5 Acquisition	p. 333
13.1.6 Retention	p. 334
13.1.7 Cross-selling and up-selling	p. 335
13.1.8 Market basket analysis	p. 335
13.1.9 Web mining	p. 336
13.2 Salesforce management	p. 338
13.2.1 Decision processes in salesforce management	p. 339
13.2.2 Models for salesforce management	p. 342
13.2.3 Response functions	p. 343
13.2.4 Sales territory design	p. 346
13.2.5 Calls and product presentations planning	p. 347
13.3 Business case studies	p. 352
13.3.1 Retention in telecommunications	p. 352
13.3.2 Acquisition in the automotive industry	p. 354
13.3.3 Cross-selling in the retail industry	p. 358
13.4 Notes and readings	p. 360
14 Logistic and production models	p. 361
14.1 Supply chain optimization	p. 362
14.2 Optimization models for logistics planning	p. 364
14.2.1 Tactical planning	p. 364
14.2.2 Extra capacity	p. 365
14.2.3 Multiple resources	p. 366
14.2.4 Backlogging	p. 366
14.2.5 Minimum lots and fixed costs	p. 369
14.2.6 Bill of materials	p. 370
14.2.7 Multiple plants	p. 371
14.3 Revenue management systems	p. 372
14.3.1 Decision processes in revenue management	p. 373
14.4 Business case studies	p. 376
14.4.1 Logistics planning in the food industry	p. 376
14.4.2 Logistics planning in the packaging industry	p. 383
14.5 Notes and readings	p. 384
15 Data envelopment analysis	p. 385
15.1 Efficiency measures	p. 386
15.2 Efficient frontier	p. 386
15.3 The CCR model	p. 390
15.3.1 Definition of target objectives	p. 392
15.3.2 Peer groups	p. 393
15.4 Identification of good operating practices	p. 394
15.4.1 Cross-efficiency analysis	p. 394
15.4.2 Virtual inputs and virtual outputs	p. 395
15.4.3 Weight restrictions	p. 396
15.5 Other models	p. 396
15.6 Notes and readings	p. 397
Appendix A Software tools	p. 399
Appendix B Dataset repositories	p. 401
References	p. 403
Index	p. 413

Available:*

On Order

Summary

Summary

Author Notes

Table of Contents