Time-aware sequence model for next-item recommendation
- PDF / 1,738,609 Bytes
- 15 Pages / 595.224 x 790.955 pts Page_size
- 2 Downloads / 301 Views
Time-aware sequence model for next-item recommendation Dongjing Wang1 · Dengwei Xu1 · Dongjin Yu1
· Guandong Xu2
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The sequences of users’ behaviors generally indicate their preferences, and they can be used to improve next-item prediction in sequential recommendation. Unfortunately, users’ behaviors may change over time, making it difficult to capture users’ dynamic preferences directly from recent sequences of behaviors. Traditional methods such as Markov Chains (MC), Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) networks only consider the relative order of items in a sequence and ignore important time information such as the time interval and duration in the sequence. In this paper, we propose a novel sequential recommendation model, named Interval- and Duration-aware LSTM with Embedding layer and Coupled input and forget gate (IDLSTM-EC), which leverages time interval and duration information to accurately capture users’ long-term and short-term preferences. In particular, the model incorporates global context information about sequences in the input layer to make better use of long-term memory. Furthermore, the model introduces the coupled input and forget gate and embedding layer to further improve efficiency and effectiveness. Experiments on real-world datasets show that the proposed approaches outperform the state-of-the-art baselines and can handle the problem of data sparsity effectively. Keywords Recommendation · Sequence Modeling · Time-Aware · Long Short-Term Memory
1 Introduction Nowadays, people are influenced to a large extent by the massive (and overwhelming) quantity of information that This research was supported by Zhejiang Provincial Natural Science Foundation of China under No. LQ20F020015, and the Fundamental Research Funds for the Provincial University of Zhejiang by Hangzhou Dianzi University under No. GK199900299012-017. Dongjin Yu
[email protected] Dongjing Wang [email protected] Dengwei Xu [email protected] Guandong Xu [email protected] 1
School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China
2
Advanced Analytics Institute, University of Technology, Sydney, Australia
has become available due to rapid development of the Internet and Information Technology (IT), which is known as the information overload problem [3]. Consequently, it is becoming increasingly difficult for users to find the information they really need. Therefore, recommender systems have been proposed to help users find the contents that they want, such as research articles [8], point-of-interest [20, 33], questions [4] and music [23, 24]. Existing recommendation methods include collaborative filtering-based recommendations [12, 30], content-based recommendations [16], social network-based recommendations [1, 13] and hybrid recommendation [7]. For many real-world applications, such as listening to music and game playing, users usually perform a series of actions within a pe
Data Loading...
