E-Commerce Customer Retention Analysis

Sugumaran, Mohan (2024) E-Commerce Customer Retention Analysis. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (471kB) | Preview

Abstract

In the highly competitive e-commerce industry, businesses encounter substantial difficulties in maintaining their current clients due to the ease of transitioning between platforms and the multitude of options available. Consequently, corporations in this fiercely competitive market struggle to maintain customer loyalty. The customer attrition poses a significant risk to the financial stability and long-term viability of an organisation. This project aims to provide a comprehensive machine learning system that can anticipate client churn and enable proactive customer retention measures. A thorough data analysis focusses on Tenure, City_Tier, Payment methods, Gender, and Service_Score. Handling missing data, encoding categorical variables, and normalising numerical characteristics are data preparation tasks. SMOTE is used to equalise the dataset. Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, AdaBoost, Bagging, Support Vector Machine, and Naive Bayes are evaluated. GridSearchCV adjusts hyperparameters to improve model performance. Models are evaluated on accuracy, precision, recall, and F1 score, focusing on recall. Gradient Boosting, the best model with 0.95 accuracy and 0.96 recall, is used with Streamlit to provide real-time churn estimates and actionable insights.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Chikkankod, Arjun UNSPECIFIED
Uncontrolled Keywords:	Customer Churn; E-commerce Retention; Data Analytics; Machine Learning Prediction; SMOTE; Gradient Boosting; Predictive Modelling
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Marketing > Consumer Behaviour H Social Sciences > HF Commerce > Electronic Commerce Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	26 Aug 2025 11:31
Last Modified:	26 Aug 2025 11:31
URI:	https://norma.ncirl.ie/id/eprint/8640

Actions (login required)

View Item