Top-N recommendations in the presence of sparsity: An NCD-based approach

TL;DR

This paper introduces an NCD-based method for top-N recommendations that effectively addresses sparsity by exploiting the hierarchical structure of item space, improving accuracy and diversity in cold-start scenarios.

Contribution

The work presents a novel NCD-based approach that models item space as Nearly Decomposable, providing theoretical guarantees and outperforming existing algorithms in sparse data settings.

Findings

Outperforms state-of-the-art algorithms in accuracy and diversity

Guarantees full item space coverage even in cold-start scenarios

Demonstrates robustness to data sparsity on real datasets

Abstract

Making recommendations in the presence of sparsity is known to present one of the most challenging problems faced by collaborative filtering methods. In this work we tackle this problem by exploiting the innately hierarchical structure of the item space following an approach inspired by the theory of Decomposability. We view the itemspace as a Nearly Decomposable system and we define blocks of closely related elements and corresponding indirect proximity components. We study the theoretical properties of the decomposition and we derive sufficient conditions that guarantee full item space coverage even in cold-start recommendation scenarios. A comprehensive set of experiments on the MovieLens and the Yahoo!R2Music datasets, using several widely applied performance metrics, support our model's theoretically predicted properties and verify that NCDREC outperforms several state-of-the-art algorithms, in terms of recommendation accuracy, diversity and sparseness insensitivity.