Cause-Based Unsupervised Risk Profiling of Injury-Involved Traffic Accidents with Post-Hoc Severity Validation

Yasin Sancar; Sinan Oztas; Esma Kececi

doi:10.48084/etasr.17465

Authors

Yasin Sancar Faculty of Open and Distance Education, Ataturk University, Erzurum, Turkiye
Sinan Oztas Department of Industrial Engineering, Ataturk University, Erzurum, Turkiye
Esma Kececi Institute of Natural Sciences, Ataturk University, Erzurum, Turkiye

Volume: 16 | Issue: 3 | Pages: 36942-36948 | June 2026 | https://doi.org/10.48084/etasr.17465

Received: 11 January 2026 | Revised: 23 February 2026, 6 March 2026, and 18 March 2026 | Accepted: 19 March 2026 | Online: 6 June 2026

Corresponding author: Yasin Sancar

Abstract

Understanding the heterogeneous nature of traffic accidents is significant for developing effective road safety policies and targeted preventive strategies. In this study, traffic accidents were examined independently of outcome variables, and an analytical framework based on accident-based risk profiling was proposed. The dataset used, consisting of official traffic accident records involving injuries, was converted into an accident-based structure using unique accident identifiers, yielding a more compact and interpretable representation for analysis. To enhance interpretability and reduce noise, the dataset was limited to summary variables related to road characteristics, environmental conditions, accident types, and vehicle and driver attributes. In addition, risk profiles were derived using the K-Means clustering method within an unsupervised learning framework. Only variables representing the structural conditions under which the accident occurred were included in the clustering process, while the number of deaths and injuries was excluded to prevent outcome leakage. Following clustering, a continuous severity score was defined, assigning a higher weight to accidents with fatalities, to compare the severity levels of the risk profiles. The results revealed the existence of four distinct and balanced risk profiles that were found to differ significantly in terms of accident severity, accident types, speed limits, and temporal distributions. The highest-risk profile was associated with run-off-road and rollover accidents occurring on roads with high speed limits, whereas lower-risk profiles were primarily characterized by contact-related accident types on roads with lower speed limits. These findings indicate that evaluating traffic accidents based on structural risk profiles, rather than solely on frequency or binary severity classes, provides more informative results. The proposed approach offers a practical methodological framework for developing decision support systems in traffic safety and for formulating targeted preventive policies.

Keywords:

traffic accidents, risk profiling, unsupervised learning, severity analysis

References

Z. Zhang, Z. Niu, Y. Li, X. Ma, and S. Sun, "Research on the influence factors of accident severity of new energy vehicles based on ensemble learning," Frontiers in Energy Research, vol. 11, Nov. 2023, Art. no. 1329688.

P. Manoj, K. C. Manjunath, and P. B. Kotagi, "Machine Learning Models for Proactive Road Safety: Evaluating Regression and Ensemble Techniques Based on Road Geometry," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 25951–25958, Aug. 2025.

S. Ahmed, M. A. Hossain, S. K. Ray, M. M. I. Bhuiyan, and S. R. Sabuj, "A study on road accident prediction and contributing factors using explainable machine learning models: analysis and performance," Transportation Research Interdisciplinary Perspectives, vol. 19, May 2023, Art. no. 100814.

A. B. Parsa, A. Movahedi, H. Taghipour, S. Derrible, and A. (Kouros) Mohammadian, "Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis," Accident Analysis & Prevention, vol. 136, Mar. 2020, Art. no. 105405.

S. Dong, A. Khattak, I. Ullah, J. Zhou, and A. Hussain, "Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations," International Journal of Environmental Research and Public Health, vol. 19, no. 5, Mar. 2022, Art. no. 2925.

I. Abdulrashid, R. Zanjirani Farahani, S. Mammadov, M. Khalafalla, and W.-C. Chiang, "Explainable artificial intelligence in transport Logistics: Risk analysis for road accidents," Transportation Research Part E: Logistics and Transportation Review, vol. 186, June 2024, Art. no. 103563.

A. K. Rifat, A. Kabir, and A. Huq, "An Explainable Machine Learning Approach to Traffic Accident Fatality Prediction," Procedia Computer Science, vol. 246, pp. 1905–1914, 2024.

I. Abdulrashid, W.-C. Chiang, J.-B. Sheu, and S. Mammadov, "An interpretable machine learning framework for enhancing road transportation safety," Transportation Research Part E: Logistics and Transportation Review, vol. 195, Mar. 2025, Art. no. 103969.

M. Awad, G. S. Moussa, A. M. Wahaballa, and H. Younes, "A state-of-the-art review of injury severity analysis in traffic crashes: toward a generalized modeling framework," Innovative Infrastructure Solutions, vol. 11, no. 1, Jan. 2026, Art. no. 19.

C. K. H. Lee, E. K. H. Leung, Y. K. Tse, and Y.-C. Tsao, "Investigating collision patterns to support autonomous driving safety," Enterprise Information Systems, vol. 18, no. 2, Feb. 2024, Art. no. 2243460.

B. Zhou et al., "Comparing Factors Affecting Injury Severity of Passenger Car and Truck Drivers," IEEE Access, vol. 8, pp. 153849–153861, 2020.

D. Nikolaou, A. Ziakopoulos, A. Dragomanovits, J. Roussou, and G. Yannis, "Comparing Machine Learning Techniques for Predictions of Motorway Segment Crash Risk Level," Safety, vol. 9, no. 2, May 2023, Art. no. 32.

I. Aldhari, M. Almoshaogeh, A. Jamal, F. Alharbi, M. Alinizzi, and H. Haider, "Severity Prediction of Highway Crashes in Saudi Arabia Using Machine Learning Techniques," Applied Sciences, vol. 13, no. 1, Dec. 2022, Art. no. 233.

N. Ahmad, B. Wali, and A. J. Khattak, "Heterogeneous ensemble learning for enhanced crash forecasts – A frequentist and machine learning based stacking framework," Journal of Safety Research, vol. 84, pp. 418–434, Feb. 2023.

B. M. T. H. Anik, Z. Islam, and M. Abdel-Aty, "A time-embedded attention-based transformer for crash likelihood prediction at intersections using connected vehicle data," Transportation Research Part C: Emerging Technologies, vol. 169, Dec. 2024, Art. no. 104831.

M. K. Nour, A. Naseer, B. Alkazemi, and M. Abid, "Road Traffic Accidents Injury Data Analytics," International Journal of Advanced Computer Science and Applications, vol. 11, no. 12, 2020.

S. I. Mohammadpour, M. Khedmati, and M. J. H. Zada, "Classification of truck-involved crash severity: Dealing with missing, imbalanced, and high dimensional safety data," PLOS ONE, vol. 18, no. 3, Mar. 2023, Art. no. e0281901.

K. Islam, I. Reza, U. Gazder, R. Akter, M. Arifuzzaman, and M. M. Rahman, "Predicting Road Crash Severity Using Classifier Models and Crash Hotspots," Applied Sciences, vol. 12, no. 22, Nov. 2022, Art. no. 11354.

M. Yan and Y. Shen, "Traffic Accident Severity Prediction Based on Random Forest," Sustainability, vol. 14, no. 3, Feb. 2022, Art. no. 1729.

K. Kalair and C. Connaughton, "Dynamic and Interpretable Hazard-Based Models of Traffic Incident Durations," Frontiers in Future Transportation, vol. 2, June 2021, Art. no. 669015.

X. Chen et al., "Network-Level Safety Metrics for Overall Traffic Safety Assessment: A Case Study," IEEE Access, vol. 11, pp. 17755–17778, 2023.

X. Li, L. Shi, and C. Wu, "How Intercity Expressway Passenger Flow Varies? A View from Month, City Characteristics, and Weather at the Origin and Destination." In Review, Nov. 03, 2023.

A. N. Melo, C. Salinas, and M. A. Sotelo, "Experimental Insights Towards Explainable and Interpretable Pedestrian Crossing Prediction." arXiv, 2023.

A. Sengupta, S. Ilgin Guler, V. V. Gayah, and S. Warchol, "Evaluating the reliability of automatically generated pedestrian and bicycle crash surrogates," Accident Analysis & Prevention, vol. 203, Aug. 2024, Art. no. 107614.

R. Chakraborty and S. Das, "A Dimensionality-Reduced XAI Framework for Roundabout Crash Severity Insights." arXiv, 2025.

J. Alotaibi, "Enhancing Traffic Accident Severity Prediction: Feature Identification Using Explainable AI," Vehicles, vol. 7, no. 2, Apr. 2025, Art. no. 38.

C.-H. Cheng, J.-H. Yang, and P.-C. Liu, "Rule-based classifier based on accident frequency and three-stage dimensionality reduction for exploring the factors of road accident injuries," PLOS ONE, vol. 17, no. 8, Aug. 2022, Art. no. e0272956.

J. Ugan, M. Abdel-Aty, and Z. Islam, "Exploring the Influence of Drivers’ Visual Surroundings on Speeding Behavior." In Review, July 19, 2023.

T. Zhu, L. Wang, Y. Feng, W. Ma, and M. Abdel-Aty, "Vehicle-Group-Based Crash Risk Prediction and Interpretation on Highways," IEEE Transactions on Intelligent Transportation Systems, vol. 26, no. 6, pp. 7807–7818, June 2025.

M. T. Kashifi, "Robust spatiotemporal crash risk prediction with gated recurrent convolution network and interpretable insights from SHapley additive explanations," Engineering Applications of Artificial Intelligence, vol. 127, Jan. 2024, Art. no. 107379.