Home / Current Issue / Paper 1709109
Customer Lifetime Value Modeling for E-commerce Platforms Using Machine Learning and Big Data Analytics: A Comprehensive Framework for the US Market
Subject area: Science,Engineering and Technology · Area of research: ICT
Abstract
Customer Lifetime Value (CLV) modeling has emerged as a critical component for sustainable growth in the competitive US e-commerce landscape. This study presents a comprehensive framework for implementing machine learning and big data analytics to enhance CLV prediction accuracy and strategic decision-making. Through analysis of data from major US e-commerce platforms including Amazon, Shopify merchants, and direct-to-consumer brands, we demonstrate how advanced analytical techniques can improve CLV prediction accuracy by up to 34% compared to traditional methods. Our research introduces a hybrid modeling approach combining RFM analysis, cohort-based modeling, and ensemble machine learning algorithms, validated through real-world case studies from the US market. The findings reveal that personalized CLV models significantly outperform generic approaches, with implications for customer acquisition strategies, retention programs, and revenue optimization.
Keywords
Customer Lifetime Value, E-commerce, Machine Learning, Big Data Analytics, Predictive Modeling, Customer Analytics
How to cite this paper
@article{1709109,
author = {Akinbode, Azeez Kunle, Taiwo, Kamorudeen Abiola, Uchenna Evans-Anoruo},
title = {Customer Lifetime Value Modeling for E-commerce Platforms Using Machine Learning and Big Data Analytics: A Comprehensive Framework for the US Market},
journal = {Iconic Research And Engineering Journals},
year = {2023},
volume = {7},
number = {6},
pages = {565-577},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1709109.pdf},
abstract = {Customer Lifetime Value (CLV) modeling has emerged as a critical component for sustainable growth in the competitive US e-commerce landscape. This study presents a comprehensive framework for implementing machine learning and big data analytics to enhance CLV prediction accuracy and strategic decision-making. Through analysis of data from major US e-commerce platforms including Amazon, Shopify merchants, and direct-to-consumer brands, we demonstrate how advanced analytical techniques can improve CLV prediction accuracy by up to 34% compared to traditional methods. Our research introduces a hybrid modeling approach combining RFM analysis, cohort-based modeling, and ensemble machine learning algorithms, validated through real-world case studies from the US market. The findings reveal that personalized CLV models significantly outperform generic approaches, with implications for customer acquisition strategies, retention programs, and revenue optimization.},
keywords = {Customer Lifetime Value, E-commerce, Machine Learning, Big Data Analytics, Predictive Modeling, Customer Analytics},
month = {December},
}