An Intelligent Exploratory Approach for Product Recommendation Using Collaborative Filtering

Abstract

Recommendation systems (RS) have become a hot topic in the study, intending to assist consumers in finding goods online by offering choices that closely match their interests. Recommending a product to customers exclusively based on a quantitative review may result in the recommendation of a product that is irrelevant. Various recommendation algorithms are used by online e-commerce companies like Amazon and Flipkart to offer different choices to different customers. Amazon now uses item-to-item collaborative filtering, which expands to enormous data sets and produces high-quality real-time suggestions. This type of filtering compares the users purchased and rated items to similar things, the results are then compiled into a user-friendly list of recommendations. The goal of this research is to create a product suggestion system for an e-commerce platform that is tailored to the preferences of customers. Collaborative Filtering is one of the methods for generating suggestions. Recommend products to consumers based on their previous purchases and the ratings left by other customers who purchased comparable things. This paper discusses a model-based collaborative filtering approach, which assists in the development of predictive items for a specific user by recognizing patterns based on preferences gleaned from various user data.