Effective CRM using Predictive Analytics

Antonios Chorianopoulos

ISBN: 9788126567331

388 pages

INR 1329


This book aims to present the main data mining concepts and a step by step methodological framework for data mining applications in Customer Relationship Management. It is organized in three sections: Methodology, Algorithms and Case Studies. The book follows a handbook approach and all the topics are described with the use of three very popular data mining tools: IBM SPSS Modeler, the open source RapidMiner and Data Mining for Excel. A large part of the Methodology section is dedicated to presenting a specific roadmap for developing cross / deep / up selling and churn models to optimize marketing campaigns. Data mining algorithms are explained in a simple and comprehensive way for business users with no technical expertise. A specific explanation is provided for the algorithms used in the case studies for all the presented data mining tools.





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

1.4 The data

1.5 Summary


Part I The Methodology

2 Classification modeling methodology

2.1 An overview of the methodology for classification modeling

2.2 Business understanding and design of the process

2.3 Data understanding, preparation and enrichment

2.4 Classification modeling

2.5 Model evaluation

2.6 Model deployment

2.7 Using classification models in direct marketing campaigns

2.8 Acquisition modeling

2.9 Crossâ selling modeling

2.10 Offer optimization with next best product campaigns

2.11 Deepâ selling modeling

2.12 Upâ selling modeling

2.13 Voluntary churn modeling

2.14 Summary of what we've learned so far: it's not about the tool or the modeling algorithm. It's about the methodology and the design of the process


3 Behavioral segmentation methodology

3.1 An introduction to customer segmentation

3.2 An overview of the behavioral segmentation methodology

3.3 Business understanding and design of the segmentation process

3.4 Data understanding, preparation, and enrichment

3.5 Identification of the segments with cluster modeling

3.6 Evaluation and profiling of the revealed segments  

3.7 Deployment of the segmentation solution, design and delivery of differentiated strategies

3.8 Summary


Part II The Algorithms

4 Classification algorithms

4.1 Data mining algorithms for classification

4.2 An overview of Decision Trees

4.3 The main steps of Decision Tree algorithms

4.4 CART, C5.0 / C4.5 and CHAID and their attribute selection measures

4.5 Bayesian networks

4.6 Naïve Bayesian networks

4.7 Bayesian belief networks

4.8 Support vector machines

4.9 Summary


5 Segmentation algorithms

5.1 Segmenting customers with data mining algorithms

5.2 Principal components analysis

5.3 Clustering algorithms

5.4 Summary


Part III The Case Studies

6 A voluntary churn propensity model for credit card holders

6.1 The business objective

6.2 The mining approach

6.3 The data dictionary

6.4 The data preparation procedure

6.5 Derived fields: the final data dictionary

6.6 The modeling procedure

6.7 Understanding and evaluating the models

6.8 Model deployment: using churn propensities to target the retention campaign

6.9 The voluntary churn model revisited using Rapid Miner

6.10 Developing the churn model with Data Mining for Excel

6.11 Summary


7 Value segmentation and crossâ selling in retail

7.1 The business background and objective

7.2 An outline of the data preparation procedure

7.3 The data dictionary

7.4 The data preparation procedure

7.5 The data dictionary of the modeling file

7.6 Value segmentation

7.7 The recency, frequency and monetary (RFM) analysis

7.8 The RFM cell segmentation procedure

7.9 Setting up a crossâ selling model

7.10 The mining approach

7.11 The modeling procedure

7.12 Browsing the model results and assessing the predictive accuracy of the classifiers

7.13 Deploying the model and preparing the crossâ selling campaign list

7.14 The retail case study using RapidMiner

7.15 Building the cross‐selling model with Data Mining for Excel

7.16 Summary


8 Segmentation application in telecommunications

8.1 Mobile telephony: the business background and objective

8.2 The segmentation procedure

8.3 The data preparation procedure

8.4 The data dictionary and the segmentation fields

8.5 The modeling procedure

8.6 Segmentation using RapidMiner and Kâ means cluster

8.7 Summary