Skewness Ranking Optimization for Personalized Recommendation

TL;DR

This paper introduces a new optimization criterion based on the skew normal distribution to enhance personalized recommendation systems, demonstrating superior performance over existing methods on large-scale datasets.

Contribution

It proposes a novel skewness-based optimization criterion for personalized recommendation, linking it to the skew normal distribution's shape parameter and ROC curve maximization.

Findings

Outperforms state-of-the-art recommendation models

Consistently achieves best results across multiple datasets

Provides theoretical insights into the relationship with ROC curve maximization

Abstract

In this paper, we propose a novel optimization criterion that leverages features of the skew normal distribution to better model the problem of personalized recommendation. Specifically, the developed criterion borrows the concept and the flexibility of the skew normal distribution, based on which three hyperparameters are attached to the optimization criterion. Furthermore, from a theoretical point of view, we not only establish the relation between the maximization of the proposed criterion and the shape parameter in the skew normal distribution, but also provide the analogies and asymptotic analysis of the proposed criterion to maximization of the area under the ROC curve. Experimental results conducted on a range of large-scale real-world datasets show that our model significantly outperforms the state of the art and yields consistently best performance on all tested datasets.