Predicting Customer Lifetime Value (CLV) in UK and Brazil using Machine Learning and Deep Learning: A Comparative Analysis

Maliyekkal, Christy Davis (2023) Predicting Customer Lifetime Value (CLV) in UK and Brazil using Machine Learning and Deep Learning: A Comparative Analysis. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (507kB) | Preview

Abstract

Understanding and efficiently deciding Customer Lifetime Value (CLV) is essential for keeping competitive advantage in the modern era of e-commerce. This study aims to taking into account the differences between two very different markets: Brazil and the United Kingdom, to clarify the complex effectiveness of CLV. The primary objective is to provide insightful information that helps companies operating in these various e-commerce environments make more informed decisions. The project is organized, starting with a careful data collection procedure to guarantee a thorough portrayal of customer behavior and transactions. The datasets from Brazil and the UK form the basis for the studies that follow. The XGB Regressor, Support Vector Machine (SVM), and Random Forest algorithms are used to model CLV trends for each market under the machine learning framework. Moreover, the deep learning technique makes use of the Multilayer Perceptron (MLP) Regressor to identify complexities and connections in the data. The Brazilian e-commerce market performed better than the UK e-commerce by showing better performance in accuracy and error pattern. Random Forest and MLP Regressor are the better performed algorithms. A comparison of the models that clarifies the advantages and disadvantages of each strategy. The results not only further our understanding of CLV but also provide useful information for companies looking to adjust their strategy to the particularities of the Brazilian and UK e-commerce markets. To put it simply, our research acts as a role model for companies, helping them navigate the complex world of consumer dynamics and provide a path forward for utilizing advanced analytics to achieve long-term profitability and success.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Menghwar, Teerath Kumar UNSPECIFIED
Uncontrolled Keywords:	Customer Lifetime Value; CLV; Machine Learning; Deep Learning; XGB Regressor; SVM; Random Forest; Multi-Layer Perceptron (MLP) Regressor
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:	16 May 2025 10:45
Last Modified:	16 May 2025 10:45
URI:	https://norma.ncirl.ie/id/eprint/7565

Actions (login required)

View Item