BookCeption
Aniqa Zaida Khanom, Sheikh Mastura Farzana, Tahsinur Rahman, Iftekharul Mobin · 2019
BookCeption is a web-based book recommendation system that allows readers to browse and buy books across multiple platforms at the most affordable price. It fetches data from E-commerce sites like Barnes and Nobles, Amazon, eBay along with Facebook pages and retail bookstore websites. It is a unique book recommender that uses Machine Learning techniques to recommend books as well as offers from other platforms to the registered users. This paper introduces the architecture of the proposed framework, which integrates the book recommendation system with a platform for buying books. For the book recommender discussed here, four different recommendation techniques were used- SVD, Co-clustering, NMF and Deep Learning to determine the best one for the framework. In terms of computational training time, Co-clustering works best with a time of 5.21 minutes and RMSE value of 0.868. However, on the basis of RMSE value, Deep Learning Embedding Model works best with RMSE value of 0.7599 in 8.06 minutes when the number of epochs and the batch size are 20 and 200 respectively.