Urban Development Policy Making

Urban Development Policy Making

Comparative Evaluation of Machine Learning Algorithms for Predicting Victim Road-User Type and Road Type in Fatal Vulnerable Road User Crashes in Tehran, Iran

Document Type : Original Article

Authors
1 Assistant Professor of Geography and Urban Planning, Department of Tourism Management, Faculty of Accounting and Management, Allameh Tabataba’i University, Tehran, Iran
2 PhD of Transportation Planning, Faculty of Civil Engineering, Science and Research Branch, Islamic Azad university, Tehran, Iran
3 M.Sc. of Architecture Engineering, Faculty of Architecture and Urban Planning, Qazvin Branch, Islamic Azad university, Qazvin, Iran
10.22034/judpm.2026.595340.1146
Abstract
Traffic crashes are a major public health and urban safety challenge in Tehran, where vulnerable road users account for a substantial share of annual fatalities. Using fatal crash records from 2017 to 2025, this study applied descriptive statistics, the chi-square test, and Cramér's V to assess associations among categorical variables; eight supervised machine learning algorithms to predict deceased road-user type and road type; and K-Means clustering to identify latent patterns. Annual crash counts increased markedly. Pedestrians and motorcyclists constituted a large share of vulnerable road user fatalities, and highways were the most common crash location. Based on consistency across cross-validation folds, XGBoost performed best in predicting deceased road-user type (accuracy = 0.8091). For road type, severe class imbalance was addressed by comparing 14 imbalance-handling methods according to recall for the minority class, secondary streets (7.3% of records). Only an adjusted random forest substantially improved secondary-street recall (from 0 to 0.3333) without a marked loss in overall accuracy (0.4704). Clustering identified four profiles: Cluster 0, characterized by a notable pedestrian presence; Cluster 1, by a higher share of motorcyclists and highway crashes; Cluster 2, by pedestrian predominance and the highest proportion of hit-and-run incidents; and Cluster 3, the largest, by motorcyclist predominance. These differences underscore the need for interventions tailored to each group to improve traffic safety management in Tehran.
Keywords
Subjects

1. Godthelp H, Ksentini A. Specific road safety issues in low- and middle income countries (LMICs): an overview and some illustrative examples. Traffic Saf Res. 2024;8:e000068. doi:10.55329/sdtu9515
2. World Health Organization. Road traffic injuries \[Internet\]. Geneva: World Health Organization; \[cited September2026\]. Available from: [https\://www\.who.int/news-room/fact-sheets/detail/road-traffic-injuries](https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries)
3. Tehran Municipality, Deputy of Transportation and Traffic. Selected statistics on the identification and treatment of traffic accident black spots in Tehran in 2024 \[Persian\]. General Directorate of Traffic Engineering and Safety, Deputy of Transportation and Traffic, Tehran Municipality; 2025\.
4. Tehran Municipality, Deputy of Transportation and Traffic. Fatal traffic crash analysis report, 2025 \[Persian\]. General Directorate of Traffic Engineering and Safety, Deputy of Transportation and Traffic, Tehran Municipality; 2026\.
5. Ahmed SK, Mohammed MG, Abdulqadir SO, El-Kader RA, El-Shall N, Chandran D, et al. Road traffic accidental injuries and deaths: a neglected global health issue. Health Sci Rep. 2023;6. doi:10.1002/hsr2.1240
6.Naci H, Chisholm D, Baker T. Distribution of road traffic deaths by road user group: a global comparison. Inj Prev. 2009;15:55-9. doi:10.1136/ip.2008.018721
7. Olszewski P, Szagała P, Rabczenko D, Zielińska A. Investigating safety of vulnerable road users in selected EU countries. J Safety Res. 2019;68:49-57. doi:10.1016/j.jsr.2018.12.001
8. Yousefifard M, Toloui A, Ahmadzadeh K, Gubari MI, Neishaboori AM, Amraei F, et al. Risk factors for road traffic injury-related mortality in Iran; a systematic review and meta-analysis. Arch Acad Emerg Med. 2021;9. doi:10.22037/aaem.v9i1.1329
9. Bahadorimonfared A, Soori H, Mehrabi Y, Delpisheh A, Esmaili A, Salehi M, et al. Trends of fatal road traffic injuries in Iran (2004–2011). PLoS One. 2013;8. doi:10.1371/journal.pone.0065198
10. Taherian MR, Maleki F, Talebi M, Varnosfaderani MR, Mirtorabi S, Forouzesh M, et al. Rising trend in traffic accident mortality in Iran after a decade of decline (2006–2022): time to raise the alarm. BMC Public Health. 2025;25. doi:10.1186/s12889-025-22905-y
11. Jahanjoo F, Sadeghi-Bazargani H, Asghari-Jafarabadi M. Modeling road traffic fatalities in Iran's six most populous provinces, 2015–2016. BMC Public Health. 2022;22. doi:10.1186/s12889-022-14678-5
12. Aghasi N. Spatiotemporal analysis of urban traffic accidents: a case study of Tehran city, Journal of Geographic Information System.2018;10; 05\. DOI: 10.4236/jgis.2018.105032
13. Jamal A, Zahid M, Rahman MT, Al-Ahmadi HM, Almoshaogeh MI, Farooq D, et al. Injury severity prediction of traffic crashes with ensemble machine learning techniques: a comparative study. Int J Inj Contr Saf Promot. 2021;28:408-27. doi:10.1080/17457300.2021.1928233
14. Hamdan N, Sipos T. Advancements in machine learning for traffic accident severity prediction: a comprehensive review. Period Polytech Transp Eng. 2025\. doi:10.3311/pptr.40369
15. Zahid M, Habib MF, Ijaz M, Ameer I, Ullah I, Ahmed T, et al. Factors affecting injury severity in motorcycle crashes: different age groups analysis using Catboost and SHAP techniques. Traffic Inj Prev. 2024;25:472-81. doi:10.1080/15389588.2023.2297168
16.Komol MMR, Hasan MM, Elhenawy M, Yasmin S, Masoud M, Rakotonirainy A. Crash severity analysis of vulnerable road users using machine learning. PLoS One. 2021;16. doi:10.1371/journal.pone.0255828
17. Wu S, Yuan Q, Yan Z, Xu Q. Analyzing accident injury severity via an extreme gradient boosting (XGBoost) model. J Adv Transp. 2021; Article ID: 771640\. doi:10.1155/2021/3771640
18.Santos D, Saias J, Quaresma P, Nogueira V. Machine learning approaches to traffic accident analysis and hotspot prediction. Computers. 2021;10:157. doi:10.3390/computers10120157
19. Shafabakhsh G, Famili A, Bahadori M. GIS-based spatial analysis of urban traffic accidents: case study in Mashhad, Iran. J Traffic Transp Eng. 2017;4:290-9. doi:10.1016/j.jtte.2017.05.005
20. Nafiiyah N, Wardhani R, Huda MN, Setyan AP, Prakasa E. K-means clustering for data-driven traffic accident in East Java. JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika). 2025\. doi:10.29100/jipi.v10i4.9236
21. Khwajeh Salimi M, Khabiri MM, Falahnejad MS. Prediction and analysis of factors associated with road traffic accidents using the support vector machine algorithm \[Persian\]. Journal of Civil Engineering and Environmental Systems. 2019\. doi:10.22034/ceej.2019.9649
22. Mohammadpour S, Mohammadzadeh Moghadam A. Analysis of road traffic accident severity in Iran using an integrated data preprocessing approach based on machine learning algorithms \[Persian\]. 2026\. Available from: https\://isnac.ir/XGFB-KDZCH
23. Tavakoli Kashani A., Medghalchi A., Mohammadi A., Jazvanaqi M. Applying Machine Learning Methods to Predict Crash Severity at Rural Roads- Case Study of Zanjan Province. Road. 2024;32(119):107-118 (In Persian). doi: 10.22034/road.2023.397089.2169
24. Ardakani SP, Liang X, Mengistu KT, So RS, Wei X, He B, et al. Road car accident prediction using a machine-learning-enabled data analysis. Sustainability. 2023;15.
25. Yassin S, Pooja P. Road accident prediction and model interpretation using a hybrid K-means and random forest algorithm approach. SN Appl Sci. 2020;2. doi:10.1007/s42452-020-3125-1
Volume 3, Issue 4 - Serial Number 9
Autumn 2027
Pages 709-732

  • Receive Date 26 June 2026
  • Revise Date 27 July 2026
  • Accept Date 22 September 2026
  • Publish Date 01 January 2027