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
Ali Agheli , Kayvan Aghabayk , Matin Sadeghi , Subasish Das
{"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","authors":"Ali Agheli , Kayvan Aghabayk , Matin Sadeghi , Subasish Das","doi":"10.1016/j.iatssr.2025.03.004","DOIUrl":null,"url":null,"abstract":"<div><div>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.</div></div>","PeriodicalId":47059,"journal":{"name":"IATSS Research","volume":"49 2","pages":"Pages 155-168"},"PeriodicalIF":3.2000,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IATSS Research","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0386111225000135","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TRANSPORTATION","Score":null,"Total":0}
引用次数: 0
Abstract
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.
期刊介绍:
First published in 1977 as an international journal sponsored by the International Association of Traffic and Safety Sciences, IATSS Research has contributed to the dissemination of interdisciplinary wisdom on ideal mobility, particularly in Asia. IATSS Research is an international refereed journal providing a platform for the exchange of scientific findings on transportation and safety across a wide range of academic fields, with particular emphasis on the links between scientific findings and practice in society and cultural contexts. IATSS Research welcomes submission of original research articles and reviews that satisfy the following conditions: 1.Relevant to transportation and safety, and the multiple impacts of transportation systems on security, human health, and the environment. 2.Contains important policy and practical implications based on scientific evidence in the applicable academic field. In addition to welcoming general submissions, IATSS Research occasionally plans and publishes special feature sections and special issues composed of invited articles addressing specific topics.