A review on Churn Prediction and Customer Segmentation using Machine Learning

Abstract

Telecom companies have a huge amount of customer data generated every data. Since acquiring new customers is a difficult task this data can be used to explain the customers’ behaviour with the company and help companies plan the retaining strategies. Customer segmentation, a technique of dividing the customer base into multiple groups of customers with similar behavior, helps in getting an idea about the company’s customers. First the data will be cleaned, analyzed, and prepared for model training. Data preparation is important in this problem since the machine learning algorithms used for these tasks perform poorly when given unprepared data. For this, feature selection techniques such as Principal Component Analysis (PCA), information gain and correlation attribute ranking filters, Linear Discriminant Analysis (LDA) can be used. Churn prediction is a supervised binary classification task and customer segmentation is an unsupervised clustering task. This study focuses on some of the churn prediction and customer segmentation techniques. With the help of these techniques, a churn prediction model to predict churn and a model to generate customer segments can be built.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 19 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.