Cargando…
Effective CRM using predictive analytics /
A step-by-step guide to data mining applications in CRM. Following a handbook approach, this book bridges the gap between analytics and their use in everyday marketing, providing guidance on solving real business problems using data mining techniques. The book is organized into three parts. Part one...
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
Chichester, West Sussex, UK :
John Wiley & Sons Inc.,
2015.
|
| Temas: | |
| Acceso en línea: | Texto completo |
Tabla de Contenidos:
- Title Page; Copyright Page; Contents; Preface; Acknowledgments; Chapter 1 An overview of data mining: The applications, the methodology, the algorithms, and the data; 1.1 The applications; 1.2 The methodology; 1.3 The algorithms; 1.3.1 Supervised models; 1.3.1.1 Classification models; 1.3.1.2 Estimation (regression) models; 1.3.1.3 Feature selection (field screening); 1.3.2 Unsupervised models; 1.3.2.1 Cluster models; 1.3.2.2 Association (affinity) and sequence models; 1.3.2.3 Dimensionality reduction models; 1.3.2.4 Record screening models; 1.4 The data; 1.4.1 The mining datamart.
- 1.4.2 The required data per industry 1.4.3 The customer "signature": from the mining datamart to the enriched, marketing reference table; 1.5 Summary; Part I The Methodology; Chapter 2 Classification modeling methodology; 2.1 An overview of the methodology for classification modeling; 2.2 Business understanding and design of the process; 2.2.1 Definition of the business objective; 2.2.2 Definition of the mining approach and of the data model; 2.2.3 Design of the modeling process; 2.2.3.1 Defining the modeling population; 2.2.3.2 Determining the modeling (analysis) level.
- 2.2.3.3 Definition of the target event and population 2.2.3.4 Deciding on time frames; 2.3 Data understanding, preparation, and enrichment; 2.3.1 Investigation of data sources; 2.3.2 Selecting the data sources to be used; 2.3.3 Data integration and aggregation; 2.3.4 Data exploration, validation, and cleaning; 2.3.5 Data transformations and enrichment; 2.3.6 Applying a validation technique; 2.3.6.1 Split or Holdout validation; 2.3.6.2 Cross or n-fold validation; 2.3.6.3 Bootstrap validation; 2.3.7 Dealing with imbalanced and rare outcomes; 2.3.7.1 Balancing; 2.3.7.2 Applying class weights.
- 2.4 Classification modeling 2.4.1 Trying different models and parameter settings; 2.4.2 Combining models; 2.4.2.1 Bagging; 2.4.2.2 Boosting; 2.4.2.3 Random Forests; 2.5 Model evaluation; 2.5.1 Thorough evaluation of the model accuracy; 2.5.1.1 Accuracy measures and confusion matrices; 2.5.1.2 Gains, Response, and Lift charts; 2.5.1.3 ROC curve; 2.5.1.4 Profit/ROI charts; 2.5.2 Evaluating a deployed model with test-control groups; 2.6 Model deployment; 2.6.1 Scoring customers to roll the marketing campaign; 2.6.1.1 Building propensity segments.
- 2.6.2 Designing a deployment procedure and disseminating the results 2.7 Using classification models in direct marketing campaigns; 2.8 Acquisition modeling; 2.8.1.1 Pilot campaign; 2.8.1.2 Profiling of high-value customers; 2.9 Cross-selling modeling; 2.9.1.1 Pilot campaign; 2.9.1.2 Product uptake; 2.9.1.3 Profiling of owners; 2.10 Offer optimization with next best product campaigns; 2.11 Deep-selling modeling; 2.11.1.1 Pilot campaign; 2.11.1.2 Usage increase; 2.11.1.3 Profiling of customers with heavy product usage; 2.12 Up-selling modeling; 2.12.1.1 Pilot campaign; 2.12.1.2 Product upgrade.