Trusted Knowledge Infusion Model-based Recommender System for IoT based B2B applications

Abstract

The exponential growth and usage of Internet, social sites, and e-commerce results extensive amount of information everywhere. It becomes very difficult for the people to search something, so they go for the offered suggestions which are pertinent for them rather than searching from a potentially overwhelming number of options. Recommender Systems are the solutions for such difficulties. There are many powerful Recommender Systems available for e-commerce, websites, books, tourism, and documents, but recommendations for IoT-based applications need of new discoveries. Traditional recommendations methods are not sufficient for big data based scalable and heterogeneous IoT environment. In this paper, we propose a knowledge infusion model-based hybrid recommendation model for IoT-based B2B applications. The proposed model is analyzed with a real dataset, and the evaluation represents that model performs well in terms execution time, RMSE, precision and F1-score as compared with the existing models.