CUSTOMER CHURN PREDICTION IN RETAIL STORES

As we know that customer plays an important role for any business. The more customers you have the more your business grows. Once customer is added to your business, you keep the customer in track and prevent him from churning as it is your business interest. my project is based on customer

Project Title

Project Area of Specialization

Artificial Intelligence

Project Summary

my project is based on customer churnning in retail store.

Project Objectives

•Highlights the main variable/factor influencing the customer churn

•The main objective that we are trying to achieve is to let the company know, with a greater accuracy, when its customer is likely to be churn and what measures should be taken to avoid him/her from churning

•Customer retention is the main objective

Project Implementation Method

For this project we need to have the data of a retail store where customers are registered with a unique id. So we need to concern to one of the retail store which fall in the above mentioned category.

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves. We will use some machine learning algorithms on the data that we extracted by the EDA (Exploratory Data Analysis). [1] The machine learning algorithms that we have planned to use are

Decision Trees
Logistic Regression
K-Nearest Neighbors
Random Forest
XG Boost

Benefits of the Project

•Telecommunications companies like (Telenor, Zong, Mobilink etc.) produces a large amount of data from which they want to take some benefits e.g. finding out which customer is going to leave these network, who to give packages & promotions, how to attract people for the network, how to retain customer and prevent customer turnover, and hence by predicting these companies can gain high profit with it.

Technical Details of Final Deliverable

Predicting customer churn has become a ubiquitous activity in any industry. Keeping existing customers is several times more cost effective than on boarding new ones. It has been shown that existing customer base brings more revenue to the business and have higher margin. Also, up and cross selling to existing customer base is easier and more likely.

For these reasons organizations want to have a good churn prediction system.

From a modelling point of view there are two usual approaches to modelling churn:

Survival approach, where we model time to churn or time to next purchase
Classification approach, where we model the probability that a customer will churn in a certain time period in the future.[1]

For example in any retail store they can find;