Abstract
<h2>Abstract</h2> Implicit Trust-Network approach and Recommendation Methodology are employed following the building of a recommender system to improve prediction precision and recommendation quality. Implicit trust-network enhances the prediction exactness of users' preference in the system. The recommendation methodology increases the quality of recommendations. Both methods of implicit trust-network and recommendation methodology are combined to introduce a new robust recommender system called Implicit Trust-Network-based Recommendation Methodology (ITNRM). An open-source ITNRM by MATLAB is prepared to be available with no external dependencies to employ or further extension.
Highlights
Today, any business especially e-commerce like Amazon and Netflix applies Recommender Systems (RS) to discover their customers’ desires
In the implicit trust-network construction part, Implicit Trust-Network-based Recommendation Methodology (ITNRM) implicitly constructs a network of trusted users for the active user
In the recommendation methodology part, a novel merged method was defined based on the implicit trust network for ITNRM
Summary
Any business especially e-commerce like Amazon and Netflix applies Recommender Systems (RS) to discover their customers’ desires. Collaborative filtering methods recommend items through preferences (ratings) of users who are similar to active users. In the implicit trust-network construction part, ITNRM implicitly constructs a network of trusted users for the active user It utilizes three criteria of Similarity, Confidence, and Identical Opinion. In the recommendation methodology part, a novel merged method was defined based on the implicit trust network for ITNRM. The ITNRM implicitly constructs a trust-network for active users by a new approach. It uses the trust-network as the neighbor users to predict unknown-items rating accurately. For this aim, users’ trust amount is directly determined based on the proposed criteria (similarity, confidence, and identical opinion).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.