Improving E-commerce Platforms with Collaborative Filtering algorithms for Product Recommendations

Abstract

Online product reviews play a major role in the success or failure of an e-commerce business. In a transaction, buyers will usually find out information on the use of the product or service from online reviews posted by previous customers to get detailed product recommendations and make purchase decisions. Many reviews are created by users who often include strong sentimental opinions. This review of data is very promising and can be used by both customers and the Company. Customers can read reviews to know more about the quality of a product. However, due to the large number of reviews, it is difficult to see and read all consumer evaluations personally to get useful information. One effective approach in providing such recommendations is using Collaborative Filtering (CF) algorithms. This research aims to improve e-commerce platforms by applying Collaborative Filtering algorithms to provide more accurate and relevant product recommendations to users.