Predicting Customer Behavior in E-Commerce Using Machine Learning Algorithms: a Mathematical Approach

EasyChair Preprint 15678

Abstract

In recent years, the e-commerce sector has witnessed an explosive growth, with vast amounts
of data generated from customer interactions. Predicting customer behavior is crucial for
businesses to optimize marketing strategies and improve customer retention. This paper
explores the application of machine learning (ML) algorithms to predict customer behavior in
e-commerce platforms. We focus on supervised and unsupervised learning techniques,
presenting a mathematical formulation of key algorithms such as decision trees, neural
networks, and clustering. The performance of these models is evaluated using precision,
recall, and F1-score to gauge their predictive accuracy.

Keyphrases: Optimization, algorithm, machine learning, neural network

@booklet{EasyChair:15678,
  author    = {Varoon Raja and James Kung},
  title     = {Predicting Customer Behavior in E-Commerce Using Machine Learning Algorithms: a Mathematical Approach},
  howpublished = {EasyChair Preprint 15678},
  year      = {EasyChair, 2025}}