Business Intelligence: Data Mining and Optimization for Decision Making

Contents ......Page 5
Preface ......Page 12
I Components of the  decision-making  process ......Page 18
1.1 Effective and timely decisions ......Page 19
1.2 Data, information and knowledge ......Page 22
1.3 The role of mathematical models ......Page 24
1.4 Business intelligence architectures ......Page 25
1.4.1 Cycle of a business intelligence analysis ......Page 27
1.4.2 Enabling factors in business intelligence projects ......Page 29
1.4.3 Development of a business intelligence system ......Page 30
1.5 Ethics and business intelligence ......Page 33
1.6 Notes and readings ......Page 34
2.1 Definition of system ......Page 36
2.2 Representation of the decision-making process ......Page 38
2.2.1 Rationality and problem solving ......Page 39
2.2.2 The decision-making process ......Page 40
2.2.3 Types of decisions ......Page 44
2.2.4 Approaches to the decision-making process ......Page 48
2.3 Evolution of information systems ......Page 50
2.4 Definition of decision support system ......Page 51
2.5 Development of a  decision support system ......Page 55
2.6 Notes and readings ......Page 58
3.1 Definition of data warehouse ......Page 59
3.1.1 Data marts ......Page 63
3.1.2 Data quality ......Page 64
3.2 Data  warehouse architecture ......Page 65
3.2.1 ETL tools ......Page 67
3.2.2 Metadata ......Page 68
3.3 Cubes and multidimensional analysis ......Page 69
3.3.1 Hierarchies of concepts and OLAP operations ......Page 74
3.3.2 Materialization of cubes of data ......Page 75
3.4 Notes and readings ......Page 76
II Mathematical models and methods ......Page 77
4.1 Structure of mathematical models ......Page 78
4.2 Development of a model ......Page 80
4.3 Classes of  models ......Page 83
4.4 Notes and readings ......Page 88
5.1 Definition of data mining ......Page 89
5.1.1 Models and methods for data mining ......Page 91
5.1.2 Data mining,classical statistics and OLAP ......Page 92
5.1.3 Applications of data mining ......Page 93
5.2 Representation of input data ......Page 94
5.3 Data mining process ......Page 96
5.4 Analysis methodologies ......Page 102
5.5 Notes and readings ......Page 106
6.1 Data validation ......Page 107
6.1.1 Incomplete data ......Page 108
6.1.2 Data affected by noise ......Page 109
6.2.1 Standardization ......Page 111
6.3 Data reduction ......Page 112
6.3.1 Sampling ......Page 113
6.3.2 Feature selection ......Page 114
6.3.3 Principal component analysis ......Page 116
6.3.4 Data discretization ......Page 121
7.1 Univariate analysis ......Page 124
7.1.1 Graphical analysis of categorical attributes ......Page 125
7.1.2 Graphical analysis of numerical attributes ......Page 127
7.1.3 Measures of central tendency for numerical attributes ......Page 129
7.1.4 Measures of dispersion for numerical attributes ......Page 132
7.1.5 Measures of relative location for numerical attributes ......Page 137
7.1.6 Identification of outliers for numerical attributes ......Page 138
7.1.7 Measures of heterogeneity for categorical attributes ......Page 140
7.1.8 Analysis of the empirical density ......Page 141
7.1.9 Summary statistics ......Page 146
7.2.1 Graphical analysis ......Page 147
7.2.2 Measures of correlation for numerical attributes ......Page 153
7.2.3 Contingency tables for categorical attributes ......Page 156
7.3.1 Graphical analysis ......Page 158
7.3.2 Measures of correlation for numerical attributes ......Page 160
7.4 Notes and readings ......Page 163
8.1 Structure of regression models ......Page 164
8.2 Simple linear regression ......Page 167
8.2.1 Calculating the regression line ......Page 169
8.3 Multiple linear regression ......Page 172
8.3.1 Calculating the regression coefficients ......Page 173
8.3.2 Assumptions on the residuals ......Page 174
8.3.3 Treatment of categorical predictive attributes ......Page 177
8.3.4 Ridge regression ......Page 178
8.4 Validation of regression models ......Page 179
8.4.1 Normality and independence of the residuals ......Page 180
8.4.2 Significance of the coefficients ......Page 183
8.4.3 Analysis of variance ......Page 185
8.4.4 Coefficient of determination ......Page 186
8.4.5 Coefficient of linear correlation ......Page 187
8.4.6 Multicollinearity of the independent variables ......Page 188
8.4.7 Confidence and prediction limits ......Page 189
8.5 Selection of predictive variables ......Page 190
8.5.1 Example of development of a regression model ......Page 191
8.6 Notes and readings ......Page 196
9.1 Definition of time series ......Page 197
9.1.1 Index numbers ......Page 200
9.2.1 Distortion measures ......Page 202
9.2.2 Dispersion measures ......Page 203
9.2.3 Tracking signal ......Page 204
9.3 Analysis of the components of time series ......Page 205
9.3.1 Moving average ......Page 206
9.3.2 Decomposition of a time series ......Page 208
9.4.1 Simple exponential smoothing ......Page 213
9.4.2 Exponential smoothing with trend adjustment ......Page 214
9.4.3 Exponential smoothing with trend and seasonality ......Page 216
9.4.4 Simple adaptive exponential smoothing ......Page 217
9.4.5 Exponential smoothing with damped trend ......Page 218
9.4.7 Removal of trend and seasonality ......Page 219
9.5 Autoregressive models ......Page 220
9.5.3 Autoregressive integrated moving average models ......Page 222
9.5.4 Identification of autoregressive models ......Page 223
9.6 Combination of predictive models ......Page 226
9.7.1 Characteristics of the forecasting process ......Page 227
9.8 Notes and readings ......Page 229
10.1 Classification problems ......Page 230
10.1.1 Taxonomy of classification models ......Page 233
10.2 Evaluation of classification models ......Page 235
10.2.2 Repeated random sampling ......Page 237
10.2.3 Cross-validation ......Page 238
10.2.4 Confusion matrices ......Page 239
10.2.5 ROC curve charts ......Page 242
10.2.6 Cumulative gain and lift charts ......Page 243
10.3 Classification trees ......Page 245
10.3.1 Splitting rules ......Page 249
10.3.2 Univariate splitting criteria ......Page 252
10.3.3 Example of development of a classification tree ......Page 255
10.3.4 Stopping criteria and pruning rules ......Page 259
10.4 Bayesian methods ......Page 260
10.4.1 Naive Bayesian classifiers ......Page 261
10.4.2 Example of naive Bayes classifier ......Page 262
10.4.3 Bayesian networks ......Page 265
10.5 Logistic regression ......Page 266
10.6.1 The Rosenblatt perceptron ......Page 268
10.6.2 Multi-level feed-forward networks ......Page 269
10.7.1 Structural risk minimization ......Page 271
10.7.2 Maximal margin hyperplane for linear separation ......Page 275
10.7.3 Nonlinear separation ......Page 279
10.8 Notes and readings ......Page 284
11.1 Motivation and structure of association rules ......Page 285
11.2 Single-dimension association rules ......Page 289
11.3.1 Generation of frequent itemsets ......Page 292
11.3.2 Generation of strong rules ......Page 293
11.4 General association rules ......Page 296
11.5 Notes and readings ......Page 298
12.1 Clustering methods ......Page 300
12.1.1 Taxonomy of clustering methods ......Page 301
12.1.2 Affinity measures ......Page 303
12.2.1 K-means algorithm ......Page 309
12.2.2 K-medoids algorithm ......Page 312
12.3 Hierarchical methods ......Page 314
12.3.1 Agglomerative hierarchical methods ......Page 315
12.3.2 Divisive hierarchical methods ......Page 317
12.4 Evaluation of clustering models ......Page 319
12.5 Notes and readings ......Page 322
III Business intelligence applications ......Page 323
13 Marketing models ......Page 324
13.1.1 Motivations and objectives ......Page 325
13.1.2 An environment for relational marketing analysis ......Page 332
13.1.3 Lifetime value ......Page 334
13.1.4 The effect of latency in predictive models ......Page 337
13.1.5 Acquisition ......Page 338
13.1.6 Retention ......Page 339
13.1.8 Market basket analysis ......Page 340
13.1.9 Web mining ......Page 341
13.2 Salesforce management ......Page 343
13.2.1 Decision  processes in salesforce management ......Page 344
13.2.2 Models for salesforce management ......Page 347
13.2.3 Response functions ......Page 348
13.2.4 Sales territory design ......Page 351
13.2.5 Calls and product presentations planning ......Page 352
13.3.1 Retention in telecommunications ......Page 357
13.3.2 Acquisition in the automotive industry ......Page 359
13.3.3 Cross-selling in the retail industry ......Page 363
13.4 Notes and readings ......Page 365
14 Logistic and production models ......Page 366
14.1 Supply chain optimization ......Page 367
14.2.1 Tactical planning ......Page 369
14.2.2 Extra capacity ......Page 370
14.2.4 Backlogging ......Page 371
14.2.5 Minimum lots and fixed costs ......Page 374
14.2.6 Bill of materials ......Page 375
14.2.7 Multiple plants ......Page 376
14.3 Revenue management systems ......Page 377
14.3.1 Decision processes in revenue management ......Page 378
14.4.1 Logistics planning in the food industry ......Page 381
14.4.2 Logistics planning in the packaging industry ......Page 388
14.5 Notes and readings ......Page 389
15 Data envelopment analysis ......Page 390
15.2 Efficient frontier ......Page 391
15.3 The CCR model ......Page 395
15.3.1 Definition of target objectives ......Page 397
15.3.2 Peer groups ......Page 398
15.4.1 Cross-efficiency analysis ......Page 399
15.4.2 Virtual inputs and virtual outputs ......Page 400
15.5 Other  models ......Page 401
15.6 Notes and readings ......Page 402
Appendix A Software tools ......Page 403
Appendix B Data set repositories ......Page 405
References ......Page 407
Index ......Page 416