Abstract
As online shopping has expanded, product recommendations on e-commerce websites have gained significance. Systems for recommending products use information about site navigation and user leave-over to suggest more products. Customers who use a product recommendation system choose better and find items more quickly. On e-commerce websites, collaborative and content-based filtering is used in product suggestion algorithms. Collaborative filtering is driven by user preference similarity and content-based filtering. While content-based filtering groups are related to products, collaboration groups are like-minded individuals. In collaborative filtering, users with similar user profiles are used during the proposal phase; in content-based filtering, users with similar product profiles are found and recommended. These techniques cannot deliver complex commodities and have slow start-up times and small element sets. Users can push the same product if they only like certain things, but they cannot recommend a new product or user who just joined the system because they are not a group member. These approaches cannot capture complex semantic relationships, making them inadequate for recommending complex products. Recent research has focused on incorporating the domain ontology into the proposition process to create a more precise and helpful suggestion. The relational qualities of the product are not covered in this study, only its category and features are. Actually, the ontology of the proposed product should be included in the suggestion system. Relational data is integrated into the recommendation engine in this study using domain ontologies. This was done to research books that people had recommended. Relational data from an online bookseller was used to test the proposed infrastructure.