Smart Supermarkets: A Unified Approach to Predicting Customer Churn with Machine Learning and Deep Learning

Parakkalayil Mathew, Sherin (2023) Smart Supermarkets: A Unified Approach to Predicting Customer Churn with Machine Learning and Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (926kB) | Preview

Abstract

Consumer churn, a key issue in many businesses, including supermarkets, necessitates the use of predictive algorithms to anticipate and reduce possible customer departures. We aim to comprehensively understand and forecast consumer turnover in the supermarket arena. This work is intended to construct a robust prediction system by leveraging a wide ensemble of machine learning and deep learning models such as SVM, Adaboost, Random Forest, XGBoost, CNN LSTM, and GRU BiLSTM. The models were built using a dataset that included customer characteristics, purchase behavior, and churn labels. The project concluded with the creation of a web application interface for predicting attrition by inputting client information. With an accuracy score of 80%, the GRU BiLSTM model emerged as the most accurate performer, proving its usefulness in grasping sequential consumer behavior. However, there were limits to real-time adaptation and dataset comprehensiveness. Future development will include incorporating real-time data sources and improving the user interface for better use. This research lays the groundwork for more robust and adaptive customer attrition prediction systems in the supermarket business.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jilani, Musfira UNSPECIFIED
Uncontrolled Keywords:	Customer Churn Prediction; Machine Learning Models; Deep Learning Models; Adaboost Classifier
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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Retail Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	20 May 2025 13:02
Last Modified:	20 May 2025 13:02
URI:	https://norma.ncirl.ie/id/eprint/7584

Actions (login required)

View Item