Recommendation Based on Users’ Long-Term and Short-Term Interests with Attention

Qiaoqiao Tan,Fang’ai Liu

doi:10.1155/2019/7586589

Abstract

Recommendations based on user behavior sequences are becoming more and more common. Some studies consider user behavior sequences as interests directly, ignoring the mining and representation of implicit features. However, user behaviors contain a lot of information, such as consumption habits and dynamic preferences. In order to better locate user interests, this paper proposes a Bi-GRU neural network with attention to model user’s long-term historical preferences and short-term consumption motivations. First, a Bi-GRU network is established to solve the long-term dependence problem in sequences, and attention mechanism is introduced to capture user interest changes related to the target item. Then, user’s short-term interaction trajectory based on self-attention is modeled to distinguish the importance of each potential feature. Finally, combined with long-term and short-term interests, the next behavior is predicted. We conducted extensive experiments on Amazon and MovieLens datasets. The experimental results demonstrate that the proposed model outperforms current state-of-the-art models in Recall and NDCG indicators. Especially in MovieLens dataset, compared with other RNN-based models, our proposed model improved at least 2.32% at Recall@20, which verifies the effectiveness of modeling long-term and short-term interest of users, respectively.

Highlights

Using historical data to predict future behaviors is the cornerstone of many recommendation systems
Most methods focus on extracting feature similarity of users or items, ignoring preference dynamics hidden in behavior sequences. e other category is the item recommendation based on behavior sequences [4,5,6], which is recorded by associated timestamps, and accumulated data can model current consumption preferences [7]
Since the recommendation system can recommend several items at a time and related items should be placed in front of the recommendation list, in order to evaluate the performance of the item recommendation model proposed in this paper, two evaluation indicators Recall and normalized discounted cumulative gain (NDCG) are used in this paper

Summary

Introduction

Using historical data to predict future behaviors is the cornerstone of many recommendation systems. User’s interaction behaviors form a sequence naturally over time, dynamically revealing user’s long-term historical preferences and short-term consumer motivations as shown, which is a typical online shopping scene for Amazon. If only current user behavior sequences are considered, similar phone cases will be recommended, as shown in green chart of Figure 1. E other category is the item recommendation based on behavior sequences [4,5,6], which is recorded by associated timestamps, and accumulated data can model current consumption preferences [7]. User’s interests in real life changes over

Methods

Results

Conclusion