Authors: P. Bhuvaneshwari; A. Nagaraja Rao
Addresses: School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India ' School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, India
Abstract: The recommendation system works as a heart in the business strategy of e-commerce. By employing various techniques and methods it recommends the desirable items to the user. Recent studies suggest by applying proper methods the accuracy of the recommendation can be improved. Traditional techniques like collaborative filtering face the cold start problem, so in this paper, we propose an optimal switching hybrid approach (OSHA) to overcome the issue. Here, K-nearest neighbour algorithm is used to predict the similar kind of users and the experimental results show that the proposed algorithm performs better than the standalone technique.
Keywords: e-commerce; collaborative filtering; cold start problem; optimal switching hybrid approach; OSHA; K-nearest neighbour.
International Journal of Intelligent Enterprise, 2021 Vol.8 No.2/3, pp.185 - 204
Received: 06 Jul 2018
Accepted: 14 Jan 2019
Published online: 05 Mar 2021 *