A new Recommender system based on target tracking: a Kalman Filter approach

TL;DR

This paper introduces a novel recommender system that utilizes Kalman filtering for target tracking in a multidimensional resource space, aiming to improve prediction accuracy of user preferences.

Contribution

It presents a new algorithm applying Kalman filters to model user movement in resource space for enhanced recommendations.

Findings

Effective tracking of user preferences demonstrated

Improved prediction accuracy over traditional methods

Potential for real-time recommendation updates

Abstract

In this paper, we propose a new approach for recommender systems based on target tracking by Kalman filtering. We assume that users and their seen resources are vectors in the multidimensional space of the categories of the resources. Knowing this space, we propose an algorithm based on a Kalman filter to track users and to predict the best prediction of their future position in the recommendation space.