Spatio-temporal prediction of shopping behaviours using taxi trajectory data

John Cartlidge; Shuhui Gong; Ruibin Bai; Yang Yue; Qingquan Li; Guoping Qiu

doi:10.1109/ICBDA.2018.8367660

Spatio-temporal prediction of shopping behaviours using taxi trajectory data

John Cartlidge, Shuhui Gong, Ruibin Bai, Yang Yue, Qingquan Li, Guoping Qiu

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

11 Citations (Scopus)

359 Downloads (Pure)

Abstract

We use taxi trajectory data (GPS data collected for 15,000 taxis at intervals of 30 seconds across three million journeys over eight days) to generate a spatio-temporal prediction of shopping behaviours in the emerging metropolitan city of Shenzhen, China. Two approaches are compared: time-series forecasting using ARIMA; and a gravity model approach, using the Huff model calibrated with Geographical Weighted Regression. Results demonstrate that ARIMA performs with significantly higher accuracy than the more traditional Huff model method. Further, we demonstrate that while the accuracy of the Huff model is constrained by model assumptions, applying time-series methods to the underlying data directly (i.e., the ARIMA method) has no such constraints, and is limited only by the amount of data available.

Original language	English
Title of host publication	2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA 2018)
Subtitle of host publication	Proceedings of a meeting held 9-12 March 2018, Shanghai, China
Publisher	IEEE Computer Society
Pages	112-116
Number of pages	5
ISBN (Electronic)	9781538647943
ISBN (Print)	9781538647950
DOIs	https://doi.org/10.1109/ICBDA.2018.8367660
Publication status	Published - Jun 2018
Event	IEEE International Conference on Big Data Analysis - East China University of Science and Technology, Shanghai, China Duration: 9 Mar 2018 → 12 Mar 2018 Conference number: 3 http://www.icbda.org

Conference

Conference	IEEE International Conference on Big Data Analysis
Abbreviated title	ICBDA 2018
Country/Territory	China
City	Shanghai
Period	9/03/18 → 12/03/18
Internet address	http://www.icbda.org

Keywords

Taxi trajectory data
Time-series analysis
ARIMA
Huff model
Geographically weighted regression
Shopping behavior

Access to Document

10.1109/ICBDA.2018.8367660Licence: Unspecified

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at https://ieeexplore.ieee.org/document/8367660/ . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 313 KBLicence: Unspecified

Handle.net

Persistent link

Cite this

@inproceedings{b93fe1cadcfe431cb2aec517bdd03be8,

title = "Spatio-temporal prediction of shopping behaviours using taxi trajectory data",

abstract = "We use taxi trajectory data (GPS data collected for 15,000 taxis at intervals of 30 seconds across three million journeys over eight days) to generate a spatio-temporal prediction of shopping behaviours in the emerging metropolitan city of Shenzhen, China. Two approaches are compared: time-series forecasting using ARIMA; and a gravity model approach, using the Huff model calibrated with Geographical Weighted Regression. Results demonstrate that ARIMA performs with significantly higher accuracy than the more traditional Huff model method. Further, we demonstrate that while the accuracy of the Huff model is constrained by model assumptions, applying time-series methods to the underlying data directly (i.e., the ARIMA method) has no such constraints, and is limited only by the amount of data available.",

keywords = "Taxi trajectory data, Time-series analysis, ARIMA, Huff model, Geographically weighted regression, Shopping behavior",

author = "John Cartlidge and Shuhui Gong and Ruibin Bai and Yang Yue and Qingquan Li and Guoping Qiu",

year = "2018",

month = jun,

doi = "10.1109/ICBDA.2018.8367660",

language = "English",

isbn = "9781538647950",

pages = "112--116",

booktitle = "2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA 2018)",

publisher = "IEEE Computer Society",

address = "United States",

note = "IEEE International Conference on Big Data Analysis , ICBDA 2018 ; Conference date: 09-03-2018 Through 12-03-2018",

url = "http://www.icbda.org",

}

Cartlidge, J, Gong, S, Bai, R, Yue, Y, Li, Q & Qiu, G 2018, Spatio-temporal prediction of shopping behaviours using taxi trajectory data. in 2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA 2018): Proceedings of a meeting held 9-12 March 2018, Shanghai, China. IEEE Computer Society, pp. 112-116, IEEE International Conference on Big Data Analysis , Shanghai, China, 9/03/18. https://doi.org/10.1109/ICBDA.2018.8367660

Spatio-temporal prediction of shopping behaviours using taxi trajectory data. / Cartlidge, John; Gong, Shuhui; Bai, Ruibin et al.

2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA 2018): Proceedings of a meeting held 9-12 March 2018, Shanghai, China. IEEE Computer Society, 2018. p. 112-116.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Spatio-temporal prediction of shopping behaviours using taxi trajectory data

AU - Cartlidge, John

AU - Gong, Shuhui

AU - Bai, Ruibin

AU - Yue, Yang

AU - Li, Qingquan

AU - Qiu, Guoping

N1 - Conference code: 3

PY - 2018/6

Y1 - 2018/6

N2 - We use taxi trajectory data (GPS data collected for 15,000 taxis at intervals of 30 seconds across three million journeys over eight days) to generate a spatio-temporal prediction of shopping behaviours in the emerging metropolitan city of Shenzhen, China. Two approaches are compared: time-series forecasting using ARIMA; and a gravity model approach, using the Huff model calibrated with Geographical Weighted Regression. Results demonstrate that ARIMA performs with significantly higher accuracy than the more traditional Huff model method. Further, we demonstrate that while the accuracy of the Huff model is constrained by model assumptions, applying time-series methods to the underlying data directly (i.e., the ARIMA method) has no such constraints, and is limited only by the amount of data available.

AB - We use taxi trajectory data (GPS data collected for 15,000 taxis at intervals of 30 seconds across three million journeys over eight days) to generate a spatio-temporal prediction of shopping behaviours in the emerging metropolitan city of Shenzhen, China. Two approaches are compared: time-series forecasting using ARIMA; and a gravity model approach, using the Huff model calibrated with Geographical Weighted Regression. Results demonstrate that ARIMA performs with significantly higher accuracy than the more traditional Huff model method. Further, we demonstrate that while the accuracy of the Huff model is constrained by model assumptions, applying time-series methods to the underlying data directly (i.e., the ARIMA method) has no such constraints, and is limited only by the amount of data available.

KW - Taxi trajectory data

KW - Time-series analysis

KW - ARIMA

KW - Huff model

KW - Geographically weighted regression

KW - Shopping behavior

U2 - 10.1109/ICBDA.2018.8367660

DO - 10.1109/ICBDA.2018.8367660

M3 - Conference Contribution (Conference Proceeding)

SN - 9781538647950

SP - 112

EP - 116

BT - 2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA 2018)

PB - IEEE Computer Society

T2 - IEEE International Conference on Big Data Analysis

Y2 - 9 March 2018 through 12 March 2018

ER -

Spatio-temporal prediction of shopping behaviours using taxi trajectory data

Abstract

Conference

Keywords

Access to Document

Handle.net

Fingerprint

Cite this