CosRec: 2D Convolutional Neural Networks for Sequential Recommendation

TL;DR

CosRec introduces a 2D convolutional neural network for sequential recommendation, effectively capturing complex item relationships and outperforming existing methods on public datasets.

Contribution

This paper presents a novel 2D CNN architecture for sequential recommendation that models pairwise item relationships directly, improving the capture of complex user behavior patterns.

Findings

Outperforms traditional and recent sequence-based methods

Achieves state-of-the-art results on public datasets

Effectively captures complex item correlations

Abstract

Sequential patterns play an important role in building modern recommender systems. To this end, several recommender systems have been built on top of Markov Chains and Recurrent Models (among others). Although these sequential models have proven successful at a range of tasks, they still struggle to uncover complex relationships nested in user purchase histories. In this paper, we argue that modeling pairwise relationships directly leads to an efficient representation of sequential features and captures complex item correlations. Specifically, we propose a 2D convolutional network for sequential recommendation (CosRec). It encodes a sequence of items into a three-way tensor; learns local features using 2D convolutional filters; and aggregates high-order interactions in a feedforward manner. Quantitative results on two public datasets show that our method outperforms both conventional methods and recent sequence-based approaches, achieving state-of-the-art performance on various evaluation metrics.