TRAINING GAINING CUSTOMER INSIGHT THROUGH DATA MINING

1. INTRODUCTION
   – The Customer Relationship Management Strategy
   – Data Mining in the CRM Framework
   – Customer Segmentation
   – Direct Marketing Campaigns
   – Market Basket and Sequence Analysis
   – Supervised Modeling
   a. Classification modeling: predicting Events, marketing application
   b. Screening models
   c. Prediction Model
   – Unsupervised Modeling Techniques
   a. Segmention with Clustering Techniques
   b. Dimensionality of Data Reduction Techniques
   c. Association or Affinity ModelingTechniques
   d. Sequence Modeling Techniques
   e. Record Screening Modeling Techniques
   – Machine Learning/Artificial Intelligence vs. Statistical Techniques
2. CUSTOMER SEGMENTATION
   a. Customer Segmentation
   – An Introduction to Customer Segmentation
   – Segmentation in Marketing
   – Segmentation Tasks and Criteria
   b. Segmentation Types in Consumer Markets
   – Value-Based Segmentation
   – Behavioral Segmentation
   – Propensity-Based Segmentation
   – Loyalty Segmentation
   – Socio-demographic and Life-Stage Segmentation
   – Needs/Attitudinal-Based Segmentation
   c. Segmentation methods
   – Behavioral Segmentation Methodology
   – Value-Based Segmentation Methodology
   d. Data mining for segmentations
   – Principal Components Analysis
   > Why consider PCA (Principle Component Analysis)
   > How Many Components Are to Be Extracted?
   > What Is the Meaning of Each Component?
   > Does the Solution Account for All the Original Fields?
   > Proceeding to the Next Steps with the Component Scores
   > Recommended PCA Options
   – Clustering Techniques
   > Data Considerations for Clustering Models
   > Clustering with K-means
   > Clustering with the TwoStep Algorithm
   > Clustering with Kohonen Network/Self-organizing Map (SOM)
   – Examining and Evaluating the Cluster Solution
   > The Number of Clusters and the Size of Each Cluster
   > Cohesion of the Clusters
   > Separation of the Clusters
   – Understanding the Clusters through Profiling
   > Profiling the Clusters
   > Additional Profiling Suggestions
   – Selecting the Optimal Cluster Solution
   – Cluster Profiling and Scoring with Supervised Models
   – An Introduction to Decision Tree Models
   > The Advantages of Using Decision Trees for Classification Modeling
   > One Goal, Different Decision Tree Algorithms: C&RT, C5.0, and CHAID
   e. Exercise Case:
   – Segmentation Application in banking
   – Segmentation Application in Telecommunication

3. DIRECT MARKETING CAMPAIGNS
a. Approaches for direct marketing
b. How’s data mining help in marketing campaign
c. Scoring in RFM analysis
d. Approach-1: Budget optimization
e. Concept of lift and gains chart
f. Approach-2: Optimizing the campaign
g. Measuring the P/L
h. Approach-3:Customer optimization
i. Find the best model: regression, neural network, decision tree
j. Confusion matrix
k. Churn/attrition model
l. Preventing Customer attrition
m. Decision tree analysis

4. MARKET BASKET AND SEQUENCE ANALYSIS
a. The RFM Analysis
– The RFM Segmentation Procedure
– RFM: Benefits, Usage, and Limitations
– Grouping Customers According to the Products They Buy
b. Studi Kasus / Praktek pemecahan masalah Gaining Customer Insight through DATA MINING