Recommendation System Based on Content Based Filtering

Abstract—A recommendation system is a subclass of information filtering systems that provide or suggests products to its target audience. Recommendation systems are widely used these days. It may be in the form of friend suggestions on Facebook, suggesting similar products on e-commerce sites, etc. Every time we use an e-commerce website, we receive product suggestions based on our prior search activity. There are numerous ways to implement recommendation systems, such as collaborative filtering, content-based filtering, hybrid filtering. This paper developed a book recommendation engine that uses a content-based filtering approach based on their previous actions. Inverse Frequency Function (TF-IDF) (Document Frequency) and cosine similarity were used to implement content-based filtering and It determines how relevant a product is to a user's interests.