Customer data prediction and analysis in e-commerce using machine learning

Customer churn is a major challenge faced by e-commerce companies, as it 
leads to loss of revenue and decreased customer loyalty. In recent years, for 
predicting and reducing client churn machine learning techniques are 
powerful tools. This research aims to explore the use of machine learning 
algorithms for predicting customer churn, annual spending, and product ontime delivery in e-commerce. The study first conducted a comprehensive 
review of the literature on customer churn in machine learning. The 
literature showed that customer churn has been predicted successfully using 
a variety of machine learning algorithms, including support vector machine
(SVM), random forest, and decision tree in various industries. To address 
this gap in the literature, the study conducted an empirical analysis of 
customer churn in e-commerce using machine learning algorithms. The data 
were then pre-processed and analyzed utilizing machine learning techniques 
for prediction. According to the study’s findings, machine learning 
algorithms are effective in predicting customer churn, and product on-time 
delivery in e-commerce. The best-performing algorithm SVM achieved an 
accuracy of 83.45% in predicting customer churn and 68.42% for product 
on-time delivery prediction.