A Probabilistic View of Neighborhood-based Recommendation Methods

TL;DR

This paper introduces a probabilistic framework for neighborhood-based recommendation methods, modeling similarity as an unobserved factor and proposing a multi-layer similarity descriptor to improve user preference estimation.

Contribution

It presents a novel probabilistic framework (PNBM) for neighborhood-based recommendations and introduces MPNBM with a multi-layer similarity descriptor for enhanced modeling.

Findings

MPNBM effectively models similarity as an unobserved factor.

MPNBM with multi-layer similarity improves preference estimation accuracy.

Empirical results demonstrate high accuracy on real-world datasets.

Abstract

Probabilistic graphic model is an elegant framework to compactly present complex real-world observations by modeling uncertainty and logical flow (conditionally independent factors). In this paper, we present a probabilistic framework of neighborhood-based recommendation methods (PNBM) in which similarity is regarded as an unobserved factor. Thus, PNBM leads the estimation of user preference to maximizing a posterior over similarity. We further introduce a novel multi-layer similarity descriptor which models and learns the joint influence of various features under PNBM, and name the new framework MPNBM. Empirical results on real-world datasets show that MPNBM allows very accurate estimation of user preferences.