An efficient collaborative recommender system for textbooks using silhouette index and K-means clustering technique
Dinesh Kumar Yadav, Rati Shukla, Vikash Singh Yadav · International Journal of Advanced Intelligence Paradigms · 2021
A recommender system provides a great platform for filtering of information and various knowledge-based management systems. They provide very good recommendation to the users so that they are able to predict the quality of the product in e-commerce. In today's research, it is very difficult to predict the accurate information regarding online products. In this research, we are going to introduce textbook-based recommender systems which uses the silhouette index and k-means clustering technique to predict the ratings of the textbooks available online based on its previous data. Initial positions of clusters are obtained and classifying the clusters by similarity of users are done by k-means clustering techniques. Our proposed recommender systems are able to predict much improved results rather than the other available state-of-the-art methods. Efficiency and performance of this newly developed recommender systems is enhanced when compared with existing systems. All experiments are done using publicly available BX-Book-Ratings datasets and achieved the MAE of 0.63 which is best among other state-of-the-art recommendation systems.