Analysis of E-Commerce User Behavior Data Analysis Model using Fuzzy Neural Network

Abstract

 E-commerce has become a globally popular and successful strategic approach. Without really having to set foot in a store, consumers may make a request and have their goods delivered to them within days, if not hours. Evaluations are becoming increasingly important since shoppers rely on them when deciding what to buy Internet. The significance of the online platform in the company is only expected to grow, making it all the more vital to learn what motivates people to go online. Predicted immediate and long-lasting effects, prior exposure, and favorable circumstances were postulated to encourage adoption. In this study, we present a fuzzy neural network (FNN) for analyzing online shoppers' habits. Anyone working to spread the word about the Internet's advantages should render it as user-friendly as feasible. Customers using an online store often do four things: browse, bookmark, add to the store, and spend. This article is grounded on its track record across many product classes and times. The real-time analytic work investigated the skew and history of user activity in the aggregate. The study findings revealed that the suggested model has provided an accuracy of 96% and computation time of 69s which shows effective analysis on user behavior in ecommerce.