Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A machine learning based approach for predicting usage efficiency of shared e-scooters using vehicle availability data

Zhao, Pengxiang LU ; Li, Aoyong and Mansourian, A LU (2022) 25th AGILE Conference on Geographic Information Science In AGILE: GIScience Series, 3, 20, 2022 3.
Abstract
Shared electric scooters (e-scooters) have been rapidly growing in popularity across Europe over the past three years, which can bring various environmental and socioeconomic benefits. However, how to further improve the usage efficiency of shared e-scooters is still a major concern for micro-mobility operators and city planners. This paper proposes a machine learning based approach to predict the usage efficiency of shared e-scooters using GPS-based vehicle availability data. First, the usage efficiency of shared e-scooters is measured with the indicator Time to Booking at the trip level. Second, ten exploratory variables in time and space are calculated as features for the prediction based on the e-scooter trips and other related data.... (More)
Shared electric scooters (e-scooters) have been rapidly growing in popularity across Europe over the past three years, which can bring various environmental and socioeconomic benefits. However, how to further improve the usage efficiency of shared e-scooters is still a major concern for micro-mobility operators and city planners. This paper proposes a machine learning based approach to predict the usage efficiency of shared e-scooters using GPS-based vehicle availability data. First, the usage efficiency of shared e-scooters is measured with the indicator Time to Booking at the trip level. Second, ten exploratory variables in time and space are calculated as features for the prediction based on the e-scooter trips and other related data. Last, three typical machine learning methods, including logistical regression, artificial neural network and random forest are applied to predict the usage efficiency by inputting the features. Besides, the variable importance is evaluated by taking the random forest model as an example. The results show that the random forest model yields the best prediction performance (accuracy = 71.2%, F1 = 78.0%), and the variables like the hour of day and POI density present high variable importance. The findings of this study will be beneficial for micro-mobility operators and city planners to design policies and strategies for further improving the usage efficiency of e-scooter sharing services. (Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Micro-mobility, E-scootersharing, Usage efficiency, Spatiotemporalanalysis, Machine learning, Vehicle availability data, Artificial Intelligence (AI), Geospatial Artificial Intelligence (GeoAI)
host publication
Artificial Intelligence in the service of Geospatial Technologies
series title
AGILE: GIScience Series, 3, 20, 2022
editor
Parseliunas, E. ; Mansourian, A. ; Partsinevelos, P. and Suziedelyte-Visockiene, J.
volume
3
publisher
Copernicus GmbH
conference name
25th AGILE Conference on Geographic Information Science
conference location
Vilnius, Lithuania
conference dates
2022-06-14 - 2022-06-17
DOI
10.5194/agile-giss-3-20-2022
language
English
LU publication?
yes
id
68f593e3-6bdc-4f62-9268-6da0e70c8606
date added to LUP
2023-09-05 10:54:51
date last changed
2023-09-18 12:40:04
@inproceedings{68f593e3-6bdc-4f62-9268-6da0e70c8606,
  abstract     = {{Shared electric scooters (e-scooters) have been rapidly growing in popularity across Europe over the past three years, which can bring various environmental and socioeconomic benefits. However, how to further improve the usage efficiency of shared e-scooters is still a major concern for micro-mobility operators and city planners. This paper proposes a machine learning based approach to predict the usage efficiency of shared e-scooters using GPS-based vehicle availability data. First, the usage efficiency of shared e-scooters is measured with the indicator Time to Booking at the trip level. Second, ten exploratory variables in time and space are calculated as features for the prediction based on the e-scooter trips and other related data. Last, three typical machine learning methods, including logistical regression, artificial neural network and random forest are applied to predict the usage efficiency by inputting the features. Besides, the variable importance is evaluated by taking the random forest model as an example. The results show that the random forest model yields the best prediction performance (accuracy = 71.2%, F1 = 78.0%), and the variables like the hour of day and POI density present high variable importance. The findings of this study will be beneficial for micro-mobility operators and city planners to design policies and strategies for further improving the usage efficiency of e-scooter sharing services.}},
  author       = {{Zhao, Pengxiang and Li, Aoyong and Mansourian, A}},
  booktitle    = {{Artificial Intelligence in the service of Geospatial Technologies}},
  editor       = {{Parseliunas, E. and Mansourian, A. and Partsinevelos, P. and Suziedelyte-Visockiene, J.}},
  keywords     = {{Micro-mobility; E-scootersharing; Usage efficiency; Spatiotemporalanalysis; Machine learning; Vehicle availability data; Artificial Intelligence (AI); Geospatial Artificial Intelligence (GeoAI)}},
  language     = {{eng}},
  publisher    = {{Copernicus GmbH}},
  series       = {{AGILE: GIScience Series, 3, 20, 2022}},
  title        = {{A machine learning based approach for predicting usage efficiency of shared e-scooters using vehicle availability data}},
  url          = {{http://dx.doi.org/10.5194/agile-giss-3-20-2022}},
  doi          = {{10.5194/agile-giss-3-20-2022}},
  volume       = {{3}},
  year         = {{2022}},
}