Data Analysis of Customer: Segmentation And Profiling of Churner Assignment

Assignment Task

Customer churn is the rate at which customers stop using a company’s product or service per period of time (e.g. month or year). The main reason we care about churn is because customer acquisition costs are generally substantially larger than the corresponding retention costs, so having a proactive churn control strategy is very important.

You are provided with Customer Churn Dataset.xlsx and you need to identify important patterns that may help in reducing customer churn. The data consists of 20 variables and 3,333 customer records. In addition to their unique ID, each customer record consists of fifteen numeric and four categorical variables. Check Customer Churn dataset – Description.pdf for more information.

Your task involves conducting an Exploratory Data Analysis1 (EDA) in Excel in order to address the following question: what characteristics make some customers more likely to churn?

Segmentation and Profiling of churners

This assignment is a continuation of the analysis of Customer Churn Dataset.xlsx described in Customer Churn dataset- Description.pdf. You now need to further the analysis by segmenting and profiling the churners there.

Your task involves application of k-Means clustering in Orange data mining software with the aim to segment and profile the churners in Customer Churn Dataset.xlsx file. By applying the k-Means clustering you need to explore how many types of churners exist and what characterizes those types. More specifically, this assignment consists of two tasks:

• (Segmentation): Establish how many types of churners there are and the size of those types. This involves dividing the churners into segments.
• (Profiling): Profile and appropriately name the identified types of churners based on the values of their shared characteristics, i.e. variables.

This Data Science has been solved by our PhD Experts at My Uni Papers.