Information filtering via biased heat conduction

TL;DR

This paper introduces a biased heat conduction algorithm for personalized recommendation systems that significantly improves both accuracy and diversity by adjusting object temperatures, outperforming standard methods on multiple datasets.

Contribution

The paper proposes a novel biased heat conduction algorithm that enhances recommendation accuracy and diversity simultaneously, addressing limitations of previous heat conduction methods.

Findings

Accuracy improved by up to 55.4% on datasets

Diversity is maintained or increased

Better identification of user tastes

Abstract

Heat conduction process has recently found its application in personalized recommendation [T. Zhou \emph{et al.}, PNAS 107, 4511 (2010)], which is of high diversity but low accuracy. By decreasing the temperatures of small-degree objects, we present an improved algorithm, called biased heat conduction (BHC), which could simultaneously enhance the accuracy and diversity. Extensive experimental analyses demonstrate that the accuracy on MovieLens, Netflix and Delicious datasets could be improved by 43.5%, 55.4% and 19.2% compared with the standard heat conduction algorithm, and the diversity is also increased or approximately unchanged. Further statistical analyses suggest that the present algorithm could simultaneously identify users' mainstream and special tastes, resulting in better performance than the standard heat conduction algorithm. This work provides a creditable way for highly efficient information filtering.