Improving Recommendation Relevance by simulating User Interest

TL;DR

This paper proposes a method to improve recommendation relevance by dynamically adjusting item similarity ranks based on user activity, enhancing recency and relevance in online recommendation systems.

Contribution

It introduces a simple, transparent algorithm for maintaining recommendation recency through iterative rank reduction of inactive items, with a patented approach.

Findings

Enhanced recommendation relevance through recency adjustment

Algorithm effectively maintains up-to-date item rankings

Applicable to real-time online recommendation systems

Abstract

Most if not all on-line item-to-item recommendation systems rely on estimation of a distance like measure (rank) of similarity between items. For on-line recommendation systems, time sensitivity of this similarity measure is extremely important. We observe that recommendation "recency" can be straightforwardly and transparently maintained by iterative reduction of ranks of inactive items. The paper briefly summarizes algorithmic developments based on this self-explanatory observation. The basic idea behind this work is patented in a context of online recommendation systems.