Context-aware deep model for joint mobility and time prediction
Mobility prediction, which is to predict where a user will arrive based on the user's historical mobility records, has attracted much attention. We argue that it is more useful to know not only where but also when a user will arrive next in many scenarios such as targeted advertising and taxi s...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/148163 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-148163 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1481632021-04-26T06:28:45Z Context-aware deep model for joint mobility and time prediction Chen, Yile Long, Cheng Cong, Gao Li, Chenliang School of Computer Science and Engineering Proceedings of the 13th International Conference on Web Search and Data Mining Engineering::Computer science and engineering::Information systems::Database management Mobility Time Prediction Mobility prediction, which is to predict where a user will arrive based on the user's historical mobility records, has attracted much attention. We argue that it is more useful to know not only where but also when a user will arrive next in many scenarios such as targeted advertising and taxi service. In this paper, we propose a novel context-aware deep model called DeepJMT for jointly performing mobility prediction (to know where) and time prediction (to know when). The DeepJMT model consists of (1) a hierarchical recurrent neural network (RNN) based sequential dependency encoder, which is more capable of capturing a user's mobility regularities and temporal patterns compared to vanilla RNN based models; (2) a spatial context extractor and a periodicity context extractor to extract location semantics and the user's periodicity, respectively; and (3) a co-attention based social & temporal context extractor which could extract the mobility and temporal evidence from social relationships. Experiments conducted on three real-world datasets show that DeepJMT outperforms the state-of-the-art mobility prediction and time prediction methods. Ministry of Education (MOE) Accepted version Cheng Long’s work is supported by MOE Tier 1 RG20/19 (S). 2021-04-26T06:28:45Z 2021-04-26T06:28:45Z 2020 Conference Paper Chen, Y., Long, C., Cong, G. & Li, C. (2020). Context-aware deep model for joint mobility and time prediction. Proceedings of the 13th International Conference on Web Search and Data Mining, 106-114. https://dx.doi.org/10.1145/3336191.3371837 https://hdl.handle.net/10356/148163 10.1145/3336191.3371837 106 114 en RG20/19 (S) © 2020 Association for Computing Machinery (ACM). All rights reserved. This paper was published in Proceedings of the 13th International Conference on Web Search and Data Mining and is made available with permission of Association for Computing Machinery (ACM). application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering::Information systems::Database management Mobility Time Prediction |
spellingShingle |
Engineering::Computer science and engineering::Information systems::Database management Mobility Time Prediction Chen, Yile Long, Cheng Cong, Gao Li, Chenliang Context-aware deep model for joint mobility and time prediction |
description |
Mobility prediction, which is to predict where a user will arrive based on the user's historical mobility records, has attracted much attention. We argue that it is more useful to know not only where but also when a user will arrive next in many scenarios such as targeted advertising and taxi service. In this paper, we propose a novel context-aware deep model called DeepJMT for jointly performing mobility prediction (to know where) and time prediction (to know when). The DeepJMT model consists of (1) a hierarchical recurrent neural network (RNN) based sequential dependency encoder, which is more capable of capturing a user's mobility regularities and temporal patterns compared to vanilla RNN based models; (2) a spatial context extractor and a periodicity context extractor to extract location semantics and the user's periodicity, respectively; and (3) a co-attention based social & temporal context extractor which could extract the mobility and temporal evidence from social relationships. Experiments conducted on three real-world datasets show that DeepJMT outperforms the state-of-the-art mobility prediction and time prediction methods. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Chen, Yile Long, Cheng Cong, Gao Li, Chenliang |
format |
Conference or Workshop Item |
author |
Chen, Yile Long, Cheng Cong, Gao Li, Chenliang |
author_sort |
Chen, Yile |
title |
Context-aware deep model for joint mobility and time prediction |
title_short |
Context-aware deep model for joint mobility and time prediction |
title_full |
Context-aware deep model for joint mobility and time prediction |
title_fullStr |
Context-aware deep model for joint mobility and time prediction |
title_full_unstemmed |
Context-aware deep model for joint mobility and time prediction |
title_sort |
context-aware deep model for joint mobility and time prediction |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/148163 |
_version_ |
1698713753520963584 |