Big data problem scenario:

The problem is to reduce churn ratio by 5% quarterly by analyzing CDR, credit report and billing data of telecom operators to mine out churn trends of a specific region or a specific person or and age group.

Questions:

1.Define the analysis term "Predictive ANalysis", "Clustering", "Patern recognition" and explain why they are relevant to the problem above?

2. What are the differences between estimation and classification models?

3. Select two of the methods on slide 11 (attached below) and explain how they are relevant to your problem. Select one method and explain how it would be a poor selection:

4. Describe a model validation method and at least one model quality metric

5. Which type of predictive analysis sounds most exciting to you? Why?

Algorithm Groups Types of Algorithms Linear Non-linear Fuzzy Logic Neural Probabilistic Graph Slide# 11