E-scooter crash severity in the United Kingdom: A comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variances

The increasing use of e-scooters in urban areas has raised safety concerns, necessitating research for effective safety interventions. This study analyzes three years of e-scooter crash data from the United Kingdom using statistical and machine learning methods to identify key factors influencing cr...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Agheli, Kayvan Aghabayk, Matin Sadeghi, Subasish Das
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:IATSS Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0386111225000135
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427371298390016
author Ali Agheli
Kayvan Aghabayk
Matin Sadeghi
Subasish Das
author_facet Ali Agheli
Kayvan Aghabayk
Matin Sadeghi
Subasish Das
author_sort Ali Agheli
collection DOAJ
description The increasing use of e-scooters in urban areas has raised safety concerns, necessitating research for effective safety interventions. This study analyzes three years of e-scooter crash data from the United Kingdom using statistical and machine learning methods to identify key factors influencing crash severity. We employed a random parameters logit model and investigated several machine learning algorithms, with XGBoost performing best. Analysis reveals that severe injuries are more likely in crashes involving senior riders, at night with lighting, and at T, staggered, or crossroad junctions. Further insights from the XGBoost-SHAP analysis and heterogeneity in means and variances of random parameters revealed nuanced patterns. While crashes involving female riders or crashes at give way or uncontrolled junctions typically have less severe outcomes, specific condition (young female riders or nighttime crashes at these junctions) intensify the risk of severe injuries. These insights advocate for tailored public policy adjustments and infrastructure enhancements to mitigate e-scooter risks, ensuring safer urban mobility for all demographics.
format Article
id doaj-art-9e0736cc90644efd9613b65ebb137a43
institution Kabale University
issn 0386-1112
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series IATSS Research
spelling doaj-art-9e0736cc90644efd9613b65ebb137a432025-08-20T03:29:03ZengElsevierIATSS Research0386-11122025-07-0149215516810.1016/j.iatssr.2025.03.004E-scooter crash severity in the United Kingdom: A comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variancesAli Agheli0Kayvan Aghabayk1Matin Sadeghi2Subasish Das3School of Civil Engineering, College of Engineering, University of Tehran, IranSchool of Civil Engineering, College of Engineering, University of Tehran, Iran; Corresponding author.School of Civil Engineering, College of Engineering, University of Tehran, IranIngram School of Engineering, Texas State University, San Marcos, USAThe increasing use of e-scooters in urban areas has raised safety concerns, necessitating research for effective safety interventions. This study analyzes three years of e-scooter crash data from the United Kingdom using statistical and machine learning methods to identify key factors influencing crash severity. We employed a random parameters logit model and investigated several machine learning algorithms, with XGBoost performing best. Analysis reveals that severe injuries are more likely in crashes involving senior riders, at night with lighting, and at T, staggered, or crossroad junctions. Further insights from the XGBoost-SHAP analysis and heterogeneity in means and variances of random parameters revealed nuanced patterns. While crashes involving female riders or crashes at give way or uncontrolled junctions typically have less severe outcomes, specific condition (young female riders or nighttime crashes at these junctions) intensify the risk of severe injuries. These insights advocate for tailored public policy adjustments and infrastructure enhancements to mitigate e-scooter risks, ensuring safer urban mobility for all demographics.http://www.sciencedirect.com/science/article/pii/S0386111225000135Electric scooterMicromobilityE-scooter injury severityInterpretable machine learningUnobserved heterogeneity
spellingShingle Ali Agheli
Kayvan Aghabayk
Matin Sadeghi
Subasish Das
E-scooter crash severity in the United Kingdom: A comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variances
IATSS Research
Electric scooter
Micromobility
E-scooter injury severity
Interpretable machine learning
Unobserved heterogeneity
title E-scooter crash severity in the United Kingdom: A comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variances
title_full E-scooter crash severity in the United Kingdom: A comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variances
title_fullStr E-scooter crash severity in the United Kingdom: A comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variances
title_full_unstemmed E-scooter crash severity in the United Kingdom: A comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variances
title_short E-scooter crash severity in the United Kingdom: A comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variances
title_sort e scooter crash severity in the united kingdom a comparative analysis using machine learning techniques and random parameters logit with heterogeneity in means and variances
topic Electric scooter
Micromobility
E-scooter injury severity
Interpretable machine learning
Unobserved heterogeneity
url http://www.sciencedirect.com/science/article/pii/S0386111225000135
work_keys_str_mv AT aliagheli escootercrashseverityintheunitedkingdomacomparativeanalysisusingmachinelearningtechniquesandrandomparameterslogitwithheterogeneityinmeansandvariances
AT kayvanaghabayk escootercrashseverityintheunitedkingdomacomparativeanalysisusingmachinelearningtechniquesandrandomparameterslogitwithheterogeneityinmeansandvariances
AT matinsadeghi escootercrashseverityintheunitedkingdomacomparativeanalysisusingmachinelearningtechniquesandrandomparameterslogitwithheterogeneityinmeansandvariances
AT subasishdas escootercrashseverityintheunitedkingdomacomparativeanalysisusingmachinelearningtechniquesandrandomparameterslogitwithheterogeneityinmeansandvariances