Context-Aware Recurrent Structure

Part of the SpringerBriefs in Computer Science book series (BRIEFSCOMPUTER)


To investigate and address the problem of context-aware sequential prediction, this chapter introduces a sequential prediction model, named context-aware recurrent neural networks (CA-RNNs). Instead of using the constant input matrix and transition matrix in conventional RNN models, CA-RNN uses a context-aware recurrent structure and employs context-specific input matrices and context-specific transition matrices. The context-specific input matrix captures the situations that user behaviors happen, such as time, location, weather, while the context-specific transition matrix captures the time intervals between adjacent behaviors in historical sequences.


  1. 1.
    Chen, J., Wang, C., Wang, J.: A personalized interest-forgetting Markov model for recommendations. In: AAAI, pp. 16–22 (2015)Google Scholar
  2. 2.
    Liu, Q., Wu, S., Wang, L., Tan, T.: Predicting the next location: a recurrent model with spatial and temporal contexts. In: AAAI, pp. 194–200 (2016)Google Scholar
  3. 3.
    Mikolov, T., Karafiát, M., Burget, L., Cernockỳ, J., Khudanpur, S.: Recurrent neural network based language model. In: INTERSPEECH, pp. 1045–1048 (2010)Google Scholar
  4. 4.
    Natarajan, N., Shin, D., Dhillon, I.S.: Which app will you use next?: Collaborative filtering with interactional context. In: RecSys, pp. 201–208 (2013)Google Scholar
  5. 5.
    Yang, Q., Fan, J., Wang, J., Zhou, L.: Personalizing web page recommendation via collaborative filtering and topic-aware Markov model. In: ICDM, pp. 1145–1150 (2010)Google Scholar
  6. 6.
    Yu, F., Liu, Q., Wu, S., Wang, L., Tan, T.: A dynamic recurrent model for next basket recommendation. In: SIGIR, pp. 729–732 (2016)Google Scholar

Copyright information

© The Author(s) 2017

Authors and Affiliations

  1. 1.National Laboratory of Pattern Recognition, Institute of AutomationChinese Academy of SciencesBeijingChina

Personalised recommendations