Deep multi-view spatial-temporal network for taxi demand prediction

Huaxiu Yao, Fei Wu, Jintao Ke, Xianfeng Tang, Yitian Jia, Siyu Lu, Pinghua Gong, Zhenhui Li, Jieping Ye, Didi Chuxing

Research output: Chapter in Book/Report/Conference proceedingConference contribution

59 Citations (Scopus)

Abstract

Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing popularity of taxi requesting services such as Uber and Didi Chuxing (in China), we are able to collect large-scale taxi demand data continuously. How to utilize such big data to improve the demand prediction is an interesting and critical real-world problem. Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations. Recent advances in deep learning have shown superior performance on traditionally challenging tasks such as image classification by learning the complex features and correlations from large-scale data. This breakthrough has inspired researchers to explore deep learning techniques on traffic prediction problems. However, existing methods on traffic prediction have only considered spatial relation (e.g., using CNN) or temporal relation (e.g., using LSTM) independently. We propose a Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations. Specifically, our proposed model consists of three views: temporal view (modeling correlations between future demand values with near time points via LSTM), spatial view (modeling local spatial correlation via local CNN), and semantic view (modeling correlations among regions sharing similar temporal patterns). Experiments on large-scale real taxi demand data demonstrate effectiveness of our approach over state-of-the-art methods.

Original languageEnglish (US)
Title of host publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
PublisherAAAI press
Pages2588-2595
Number of pages8
ISBN (Electronic)9781577358008
StatePublished - Jan 1 2018
Event32nd AAAI Conference on Artificial Intelligence, AAAI 2018 - New Orleans, United States
Duration: Feb 2 2018Feb 7 2018

Publication series

Name32nd AAAI Conference on Artificial Intelligence, AAAI 2018

Other

Other32nd AAAI Conference on Artificial Intelligence, AAAI 2018
CountryUnited States
CityNew Orleans
Period2/2/182/7/18

Fingerprint

Traffic congestion
Image classification
Time series
Semantics
Experiments
Deep learning
Smart city
Big data

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Yao, H., Wu, F., Ke, J., Tang, X., Jia, Y., Lu, S., ... Chuxing, D. (2018). Deep multi-view spatial-temporal network for taxi demand prediction. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (pp. 2588-2595). (32nd AAAI Conference on Artificial Intelligence, AAAI 2018). AAAI press.
Yao, Huaxiu ; Wu, Fei ; Ke, Jintao ; Tang, Xianfeng ; Jia, Yitian ; Lu, Siyu ; Gong, Pinghua ; Li, Zhenhui ; Ye, Jieping ; Chuxing, Didi. / Deep multi-view spatial-temporal network for taxi demand prediction. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. pp. 2588-2595 (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).
@inproceedings{a98d8116a2684b17bdabc50c1e1713b3,
title = "Deep multi-view spatial-temporal network for taxi demand prediction",
abstract = "Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing popularity of taxi requesting services such as Uber and Didi Chuxing (in China), we are able to collect large-scale taxi demand data continuously. How to utilize such big data to improve the demand prediction is an interesting and critical real-world problem. Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations. Recent advances in deep learning have shown superior performance on traditionally challenging tasks such as image classification by learning the complex features and correlations from large-scale data. This breakthrough has inspired researchers to explore deep learning techniques on traffic prediction problems. However, existing methods on traffic prediction have only considered spatial relation (e.g., using CNN) or temporal relation (e.g., using LSTM) independently. We propose a Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations. Specifically, our proposed model consists of three views: temporal view (modeling correlations between future demand values with near time points via LSTM), spatial view (modeling local spatial correlation via local CNN), and semantic view (modeling correlations among regions sharing similar temporal patterns). Experiments on large-scale real taxi demand data demonstrate effectiveness of our approach over state-of-the-art methods.",
author = "Huaxiu Yao and Fei Wu and Jintao Ke and Xianfeng Tang and Yitian Jia and Siyu Lu and Pinghua Gong and Zhenhui Li and Jieping Ye and Didi Chuxing",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
series = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",
publisher = "AAAI press",
pages = "2588--2595",
booktitle = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",

}

Yao, H, Wu, F, Ke, J, Tang, X, Jia, Y, Lu, S, Gong, P, Li, Z, Ye, J & Chuxing, D 2018, Deep multi-view spatial-temporal network for taxi demand prediction. in 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, AAAI press, pp. 2588-2595, 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, New Orleans, United States, 2/2/18.

Deep multi-view spatial-temporal network for taxi demand prediction. / Yao, Huaxiu; Wu, Fei; Ke, Jintao; Tang, Xianfeng; Jia, Yitian; Lu, Siyu; Gong, Pinghua; Li, Zhenhui; Ye, Jieping; Chuxing, Didi.

32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. p. 2588-2595 (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Deep multi-view spatial-temporal network for taxi demand prediction

AU - Yao, Huaxiu

AU - Wu, Fei

AU - Ke, Jintao

AU - Tang, Xianfeng

AU - Jia, Yitian

AU - Lu, Siyu

AU - Gong, Pinghua

AU - Li, Zhenhui

AU - Ye, Jieping

AU - Chuxing, Didi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing popularity of taxi requesting services such as Uber and Didi Chuxing (in China), we are able to collect large-scale taxi demand data continuously. How to utilize such big data to improve the demand prediction is an interesting and critical real-world problem. Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations. Recent advances in deep learning have shown superior performance on traditionally challenging tasks such as image classification by learning the complex features and correlations from large-scale data. This breakthrough has inspired researchers to explore deep learning techniques on traffic prediction problems. However, existing methods on traffic prediction have only considered spatial relation (e.g., using CNN) or temporal relation (e.g., using LSTM) independently. We propose a Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations. Specifically, our proposed model consists of three views: temporal view (modeling correlations between future demand values with near time points via LSTM), spatial view (modeling local spatial correlation via local CNN), and semantic view (modeling correlations among regions sharing similar temporal patterns). Experiments on large-scale real taxi demand data demonstrate effectiveness of our approach over state-of-the-art methods.

AB - Taxi demand prediction is an important building block to enabling intelligent transportation systems in a smart city. An accurate prediction model can help the city pre-allocate resources to meet travel demand and to reduce empty taxis on streets which waste energy and worsen the traffic congestion. With the increasing popularity of taxi requesting services such as Uber and Didi Chuxing (in China), we are able to collect large-scale taxi demand data continuously. How to utilize such big data to improve the demand prediction is an interesting and critical real-world problem. Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations. Recent advances in deep learning have shown superior performance on traditionally challenging tasks such as image classification by learning the complex features and correlations from large-scale data. This breakthrough has inspired researchers to explore deep learning techniques on traffic prediction problems. However, existing methods on traffic prediction have only considered spatial relation (e.g., using CNN) or temporal relation (e.g., using LSTM) independently. We propose a Deep Multi-View Spatial-Temporal Network (DMVST-Net) framework to model both spatial and temporal relations. Specifically, our proposed model consists of three views: temporal view (modeling correlations between future demand values with near time points via LSTM), spatial view (modeling local spatial correlation via local CNN), and semantic view (modeling correlations among regions sharing similar temporal patterns). Experiments on large-scale real taxi demand data demonstrate effectiveness of our approach over state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85055004792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055004792&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85055004792

T3 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

SP - 2588

EP - 2595

BT - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

PB - AAAI press

ER -

Yao H, Wu F, Ke J, Tang X, Jia Y, Lu S et al. Deep multi-view spatial-temporal network for taxi demand prediction. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press. 2018. p. 2588-2595. (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).