Spatio-temporal prediction of shopping behaviours using taxi trajectory data

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

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

14 Citations (Scopus)
408 Downloads (Pure)


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 languageEnglish
Title of host publication2018 IEEE 3rd International Conference on Big Data Analysis (ICBDA 2018)
Subtitle of host publicationProceedings of a meeting held 9-12 March 2018, Shanghai, China
PublisherIEEE Computer Society
Number of pages5
ISBN (Electronic)9781538647943
ISBN (Print)9781538647950
Publication statusPublished - Jun 2018
EventIEEE International Conference on Big Data Analysis - East China University of Science and Technology, Shanghai, China
Duration: 9 Mar 201812 Mar 2018
Conference number: 3


ConferenceIEEE International Conference on Big Data Analysis
Abbreviated titleICBDA 2018
Internet address


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


Dive into the research topics of 'Spatio-temporal prediction of shopping behaviours using taxi trajectory data'. Together they form a unique fingerprint.

Cite this