Personal recommendation using deep recurrent neural networks in NetEase

By Sai Wu, Weichao Ren, Chengchao Yu, Gang Chen, Dongxiang Zhang, Jing Zhu. 2016

136 citations recorded by the source corpus.

Each user session in an e-commerce system can be modeled as a sequence of web pages, indicating how the user interacts with the system and makes his/her purchase. A typical recommendation approach, e.g., Collaborative Filtering, generates its results at the beginning of each session, listing the most likely purchased items. However, such approach fails to exploit current viewing history of the user and hence, is unable to provide a real-time customized recommendation service. In this paper, we build a deep recurrent neural network to address the problem. The network tracks how users browse the website using multiple hidden layers. Each hidden layer models how the combinations of webpages are accessed and in what order. To reduce the processing cost, the network only records a finite number of states, while the old states collapse into a single history state. Our model refreshes the recommendation result each time when user opens a new web page. As user's session continues, the recommendation result is gradually refined. Furthermore, we integrate the recurrent neural network with a Feedfoward network which represents the user-item correlations to increase the prediction accuracy. Our approach has been applied to Kaola (http://www.kaola.com), an e-commerce website powered by the NetEase technologies. It shows a significant improvement over previous recommendation service.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Yu Zhang
3. Yaochu Jin
4. Lei Wang
5. Bing Tian Dai
6. Yi Tay
7. Jie Lu
8. Qian Zhang

In Information Systems

1. Qiang Yang
2. Jie Lu
3. Yaochu Jin
4. Qian Zhang
5. Guangneng Hu
6. Yu Zhang
7. Bing Tian Dai
8. Lei Wang

In Management Science and Operations Research

1. Qiang Yang
2. Xiangyu Zhao
3. Jiliang Tang
4. Chang Zhou
5. Yi Tay
6. Jie Lu
7. Shuai Zhang
8. Heng Tao Shen

Citations in the corpus

• AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations (2020, background): “Driven by the recent advances in deep learning, there have been increasing interests in developing deep learning based recommender systems (DLRSs) [20, 30, 34].”
• ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation (2017, methodology): “RNN based methods are studied for recommendation in academic fields in recent years, which builds the recommendation context directly from the behaviors for each user (Rendle et al. 2011; Hariri, Mobasher, and Burke 2012; Wu et al. 2016).”
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning (2018, background): “[31] designed a session-based recommendation model for real-world ecommerce website.”
• CoNet: Collaborative Cross Networks for Cross-Domain Recommendation (2018, background): “These are all shallow methods and have the difficulty in learning complex (highly nonlinear) user-item interaction relationship [6, 12, 41].”
• Artificial intelligence in recommender systems (2020, methodology): “In [98], the most recent states are modelled by an RNN to predict the next item that may attract the interests of users.”
• Deep Reinforcement Learning for List-wise Recommendations (2017, background): “[29] designed a session-based recommendation model for real-world e-commerce website.”
• Deep reinforcement learning for page-wise recommendations (2018, methodology): “. For instance, Nguyen et al.[23] proposed a personalized tag recommender system based on CNN. It utilizes constitutional and max-pooling layer to get visual features from patches of images. Wu et al.[34] designed a session-based recommendation model for real-world e-commerce website. It utilizes th”
• Deep Learning Based Recommender System (2017, methodology): “re recent click-sequences; (3) distillation the model with privileged information with a teacher model; (4) using item embedding to decrease the number of parameters for faster computation. Wu et al. [176] designed a session-based recommendation model for real-world e-commerce website. It utilizes t”
• The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers (2018, background): “visual question answering [35], [36], video captioning [37], [38], [39], [40], personal interest inference [41], [42], [43] and smart transportation [44].”
• A review on deep learning for recommender systems: challenges and remedies (2018, methodology): “Wu et al. (2016a) utilize deep RNNs to provide real-time recommendations on current user browsing patterns.”