Abstract
With the rapid rise in popularity of ecommerce application, Recommender Systems are being widely used by them to predict the response that a user will give to a given item. This prediction helps in cross selling, upselling and to increase the loyalty of their customers. However due to lack of sufficient feedback data these systems suffer from sparsity problem which leads to decline in their prediction efficiency. In this work, we have proposed and empirically demonstrated how the Transfer Learning approach using five dimensions of basic human values can be successfully used to alleviate the sparsity problem and increase the efficiency of recommender system algorithms.
Highlights
With the rapid rise in popularity of e-commerce applications and the dramatic increase in the size of data present in such applications along with the related social media data generated by customers, information filtering technique like Recommender Systems( RS) are being widely used to help the customer in finding the item they might find useful
To the best of our knowledge our work presented in this paper contributes to the existing body of knowledge in the academic and practical domain of Recommender system by proposing and empirically demonstrating for the first time the Transfer Learning (TL) approach based on Basic Human Values, as a solution to alleviate the sparisty problem in a collaborative filtering based recommender system
On the basis of the experiments conducted and the results obtained, we have successfully demonstrated empirically that TL approach using Basic Human Values can be used in to alleviate sparsity problem in RS, but they serve as more useful criteria for finding similarities between various users when compared to using the ratings as in traditional collaborative filtering algorithm
Summary
With the rapid rise in popularity of e-commerce applications and the dramatic increase in the size of data present in such applications along with the related social media data generated by customers, information filtering technique like Recommender Systems( RS) are being widely used to help the customer in finding the item they might find useful. Each user generally provides rating for only a fraction of the total items present in the system, most of the user-item pair in the utility matrix remains unrated This leads to data sparsity probem and impacts the quality of recommendations. To the best of our knowledge our work presented in this paper contributes to the existing body of knowledge in the academic and practical domain of Recommender system by proposing and empirically demonstrating for the first time the TL approach based on Basic Human Values, as a solution to alleviate the sparisty problem in a collaborative filtering based recommender system.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have