On prediction of user destination by sub-trajectory understanding: a deep learning based approach

Date

2018

Authors

Zhao, J.
Xu, J.
Zhou, R.
Zhao, P.
Liu, C.
Zhu, F.

Editors

Cuzzocrea, A.
Allan, J.
Paton, N.
Srivastava, D.
Agrawal, R.
Broder, A.
Zaki, M.
Candan, S.
Labrinidis, A.
Schuster, A.
Wang, H.

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

CIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2018 / Cuzzocrea, A., Allan, J., Paton, N., Srivastava, D., Agrawal, R., Broder, A., Zaki, M., Candan, S., Labrinidis, A., Schuster, A., Wang, H. (ed./s), pp.1413-1422

Statement of Responsibility

Jing Zhao, Jiajie Xu, S, Rui Zhou, Pengpeng Zhao, Chengfei Liu, Feng Zhu

Conference Name

ACM International Conference on Information and Knowledge Management (CIKM) (22 Oct 2018 - 26 Oct 2018 : Torino, Italy)

Abstract

Destination prediction is known as an important problem for many location based services (LBSs). Existing solutions generally apply probabilistic models to predict destinations over a sub-trajectory, but their accuracies in fine-granularity prediction are always not satisfactory due to the data sparsity problem. This paper presents a carefully designed deep learning model called TALL model for destination prediction. It not only takes advantage of the bidirectional Long Short-Term Memory (LSTM) network for sequence modeling, but also gives more attention to meaningful locations that have strong correlations w.r.t. destination by adopting attention mechanism. Furthermore, a hierarchical model that explores the fusion of multi-granularity learning capability is further proposed to improve the accuracy of prediction. Extensive experiments on Beijing and Chengdu real datasets finally demonstrate that our proposed models outperform existing methods without considering external features.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2018 Association for Computing Machinery

License

Call number

Persistent link to this record