Augmenting Recurrent Neural Networks with High-Order User-Contextual Preference for Session-Based Recommendation

TL;DR

This paper introduces an augmented RNN model that incorporates high-order user-contextual preferences using PNN, significantly improving session-based recommendation performance when rich user context data is available.

Contribution

The paper proposes a novel ARNN model that explicitly models high-order user-contextual preferences to enhance RNN session models.

Findings

ARNN outperforms baseline RNN models with rich user context.

Explicit user context modeling improves recommendation accuracy.

High-order user preferences are effectively captured by PNN.

Abstract

The recent adoption of recurrent neural networks (RNNs) for session modeling has yielded substantial performance gains compared to previous approaches. In terms of context-aware session modeling, however, the existing RNN-based models are limited in that they are not designed to explicitly model rich static user-side contexts (e.g., age, gender, location). Therefore, in this paper, we explore the utility of explicit user-side context modeling for RNN session models. Specifically, we propose an augmented RNN (ARNN) model that extracts high-order user-contextual preference using the product-based neural network (PNN) in order to augment any existing RNN session model. Evaluation results show that our proposed model outperforms the baseline RNN session model by a large margin when rich user-side contexts are available.