Road traffic accidents are one of the global safety and socioeconomic challenges. According to WHO (2024), it has caused over 1.19 million annual fatalities. It is also projected to cause economic losses, which are approximately $1.8 trillion between 2015 and 2030. In this research, machine learning (ML) approach was implemented to predict the severity of road traffic accidents and explore actionable insights for intervention. The dataset used in implementing machine learning models was collected from Victoria Road Crash incidence from the years 2012-2023. This dataset includes temporal, environmental, and infrastructure variables. The target variable is severity of the road accident which is in four classes: fatal, serious injury, minor injury, and property damage. The first part of the machine learning analysis involves feature analysis using feature importance by random forest and partial dependence plots. The feature analysis identified temporal factors like accident time and date as key influencing factors of severity. The significant peaks from feature analysis showed rush hours and late weekdays as major determinants of road accidents in Victoria. Similarly, speed zones also showed a significant influence on road accidents, and this emphasizes the correlation between higher speed limits and severe outcomes. Environmental and infrastructural factors, like lighting conditions and road geometry, showed comparatively lower impact. In the second part of the analysis, three machine learning models—Logistic Regression, Random Forest, and XGBoost—were implemented for predictive performance. Logistic Regression outperformed others with the classification of minor injuries (Class 3), with a recall of 100%. Random Forest showed slightly better balance across classes. However, all models struggled with minority classes, like fatal accidents (Class 1), due to class imbalance. Overall, the findings revealed the importance of targeted interventions during high-risk periods with stricter speed limit enforcement and improved lighting infrastructure.
References
[1]
WHO (2024) Road Traffic Injuries. Road Safety.
[2]
Chen, S., Kuhn, M., Prettner, K. and Bloom, D.E. (2019) The Global Macroeconomic Burden of Road Injuries: Estimates and Projections for 166 Countries. The Lancet Planetary Health, 3, e390-e398. https://doi.org/10.1016/s2542-5196(19)30170-6
[3]
Sharma, B.R. (2008) Road Traffic Injuries: A Major Global Public Health Crisis. Public Health, 122, 1399-1406. https://doi.org/10.1016/j.puhe.2008.06.009
[4]
Akallouch, M., Fardousse, K., Bouhoute, A. and Berrada, I. (2023) Exploring the Risk Factors Influencing the Road Accident Severity: Prediction with Explanation. 2023 International Wireless Communications and Mobile Computing (IWCMC), Marrakesh, 19-23 June 2023, 763-768. https://doi.org/10.1109/iwcmc58020.2023.10182749
[5]
Li, X., Lord, D., Zhang, Y. and Xie, Y. (2008) Predicting Motor Vehicle Crashes Using Support Vector Machine Models. Accident Analysis & Prevention, 40, 1611-1618. https://doi.org/10.1016/j.aap.2008.04.010
[6]
Wang, Y., Zhai, H., Cao, X. and Geng, X. (2023) Cause Analysis and Accident Classification of Road Traffic Accidents Based on Complex Networks. Applied Sciences, 13, Article 12963. https://doi.org/10.3390/app132312963
[7]
Tamascelli, N., Campari, A., Parhizkar, T. and Paltrinieri, N. (2024) Artificial Intelligence for Safety and Reliability: A Descriptive, Bibliometric and Interpretative Review on Machine Learning. Journal of Loss Prevention in the Process Industries, 90, Article ID: 105343. https://doi.org/10.1016/j.jlp.2024.105343
[8]
Ballamudi, V.K.R. (2019) Road Accident Analysis and Prediction Using Machine Learning Algorithmic Approaches. Asian Journal of Humanity, Art and Literature, 6, 185-192. https://doi.org/10.18034/ajhal.v6i2.529
[9]
Vanitha, R. and Swedha, M. (2023) Prediction of Road Accidents Using Machine Learning Algorithms. Middle East Journal of Applied Science & Technology, 6, 64-75. https://doi.org/10.46431/mejast.2023.6208
[10]
Ogungbire, A., Kalambay, P., Gajera, H. and Pulugurtha, S. S. (2023) Deep Learning, Machine Learning, or Statistical Models for Weather-Related Crash Severity Prediction. Mineta Transportation Institute. https://doi.org/10.31979/mti.2023.2320
[11]
Kamali, R., Mazaheri, A. and Rahimi, A. (2024) Analysis of Crash Severity at Intersections and Roundabouts Using Ordered and Generalized Ordered Probit Models. Proceedings of the 8th International Conference on Road and Rail Infrastructure (CETRA 2024), Cavtat, 15-17 May 2024. https://doi.org/10.5592/co/cetra.2024.1664
[12]
Mannering, F., Bhat, C.R., Shankar, V. and Abdel-Aty, M. (2020) Big Data, Traditional Data and the Tradeoffs between Prediction and Causality in Highway-Safety Analysis. Analytic Methods in Accident Research, 25, Article ID: 100113. https://doi.org/10.1016/j.amar.2020.100113
[13]
Roustaei, N. (2024) Application and Interpretation of Linear-Regression Analysis. Medical Hypothesis Discovery and Innovation in Ophthalmology, 13, 151-159. https://doi.org/10.51329/mehdiophthal1506
[14]
Johnston, C., McDonald, J. and Quist, K. (2019) A Generalized Ordered Probit Model. Communications in Statistics—Theory and Methods, 49, 1712-1729. https://doi.org/10.1080/03610926.2019.1565780
[15]
Ding, P., Imbens, G., Qu, Z. and Ye, Y. (2024) Computationally Efficient Estimation of Large Probit Models. arXiv: 2407.09371. https://doi.org/10.48550/arXiv.2407.09371
[16]
Pourroostaei Ardakani, S., Liang, X., Mengistu, K.T., So, R.S., Wei, X., He, B., et al. (2023) Road Car Accident Prediction Using a Machine-Learning-Enabled Data Analysis. Sustainability, 15, Article 5939. https://doi.org/10.3390/su15075939
[17]
Lee, J., Yoon, T., Kwon, S. and Lee, J. (2019) Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study. Applied Sciences, 10, Article 129. https://doi.org/10.3390/app10010129
[18]
Salih, A.M., Raisi‐Estabragh, Z., Galazzo, I.B., Radeva, P., Petersen, S.E., Lekadir, K., et al. (2024) A Perspective on Explainable Artificial Intelligence Methods: SHAP and Lime. Advanced Intelligent Systems, 7, Article ID: 2400304. https://doi.org/10.1002/aisy.202400304
[19]
Bhavyasree, N. and Dhanusree, N. (2024) Prediction of Road Accidents Using Machine Learning Algorithm. International Journal of Advance Research and Innovative Ideas in Education, 10, 154-159.
[20]
Bener, A., Yildirim, E., Özkan, T. and Lajunen, T. (2017) Driver Sleepiness, Fatigue, Careless Behaviour and Risk of Motor Vehicle Crash and Injury: Population Based Case and Control Study. Journal of Traffic and Transportation Engineering (English Edition), 4, 496-502.
[21]
Rais, W., Oulha, R., Rahal, D.D. and Lallam, M. (2024) Analysis of the Environmental Factors Contributing to Road Traffic Accidents Involving School-Aged Pedestrian Children in Urban Algerian Settings. Studies in Engineering and Exact Sciences, 5, e9521. https://doi.org/10.54021/seesv5n2-378
[22]
Bakutin, Y. (2024) Visibility and Safety of Vehicle Traffic in the Dark (Current Reality, Future Projections). Visegrad Journal on Human Rights, 3, 13-19. https://doi.org/10.61345/1339-7915.2024.3.2
[23]
Bozorg, S., Tetri, E., Kosonen, I. and Luttinen, T. (2018) The Effect of Dimmed Road Lighting and Car Headlights on Visibility in Varying Road Surface Conditions. Leukos, 14, 259-273. https://doi.org/10.1080/15502724.2018.1452152
[24]
Assi, K., Rahman, S.M., Mansoor, U. and Ratrout, N. (2020) Predicting Crash Injury Severity with Machine Learning Algorithm Synergized with Clustering Technique: A Promising Protocol. International Journal of Environmental Research and Public Health, 17, Article 5497. https://doi.org/10.3390/ijerph17155497
[25]
Wang, L. (2023) Safety Evaluation for Highway Geometric Design Based on Spatial Path Properties. Journal of Advanced Transportation, 2023, Article ID: 6685010. https://doi.org/10.1155/2023/6685010
[26]
Burlacu, A. and Mihai, A. (2023) Applications of Differential Geometry of Curves in Roads Design. Romanian Journal of Transport Infrastructure, 12, 1-13. https://doi.org/10.2478/rjti-2023-0010
[27]
Islam, M. (2023) An Exploratory Analysis of the Effects of Speed Limits on Pedestrian Injury Severities in Vehicle-Pedestrian Crashes. Journal of Transport & Health, 28, Article ID: 101561. https://doi.org/10.1016/j.jth.2022.101561
[28]
Jung, S. and Qin, X. (2023) Identifying the Local Impacts of Speed-Related Factors on Tunnel Entrance Crash Severity. Transportation Research Record: Journal of the Transportation Research Board, 2677, 730-742. https://doi.org/10.1177/03611981231167156
[29]
Mohanta, B.K., Jena, D., Mohapatra, N., Ramasubbareddy, S. and Rawal, B.S. (2022) Machine Learning Based Accident Prediction in Secure IoT Enable Transportation System. Journal of Intelligent & Fuzzy Systems, 42, 713-725. https://doi.org/10.3233/jifs-189743
[30]
Ursu, E., Minnegalieva, A., Rawat, P., Chernigovskaya, M., Tacutu, R., Sandve, G.K., Robert, P.A. and Greiff, V. (2024) Training Data Composition Determines Machine Learning Generalization and Biological Rule Discovery. bioRxiv. https://doi.org/10.1101/2024.06.17.599333
[31]
Mazurek, S. and Wielgosz, M. (2023) Assessing Dataset Quality through Decision Tree Characteristics in Autoencoder-Processed Spaces. arXiv: 2306.15392. https://doi.org/10.48550/arXiv.2306.15392
[32]
Rout, S., Mallick, R. and Kumar Sahu, S. (2023) Exploring the Significance of Feature Analysis in AI/ML Modeling. 2023 OITS International Conference on Information Technology (OCIT), Raipur, 13-15 December 2023, 580-585. https://doi.org/10.1109/ocit59427.2023.10431396
[33]
Little, C.O., Lina, D.H. and Allen, G.I. (2023) Fair Feature Importance Scores for Interpreting Tree-Based Methods and Surrogates. arXiv: 2310.04352. https://doi.org/10.48550/arXiv.2310.04352
[34]
Doyen, S., Taylor, H., Nicholas, P., Crawford, L., Young, I. and Sughrue, M.E. (2021) Hollow-tree Super: A Directional and Scalable Approach for Feature Importance in Boosted Tree Models. PLOS ONE, 16, e0258658. https://doi.org/10.1371/journal.pone.0258658
[35]
Ewald, F.K., Bothmann, L., Wright, M.N., Bischl, B., Casalicchio, G. and König, G. (2024) A Guide to Feature Importance Methods for Scientific Inference. In: Longo, L., Lapuschkin, S. and Seifert, C., Eds., Explainable Artificial Intelligence, Springer, 440-464. https://doi.org/10.1007/978-3-031-63797-1_22
[36]
Jain, N., Ghosh, S., Murthy, C.A. and Ghosh, A. (2023) A Relative Density-Based Bclustering Method for Identifying Non-Linear Feature Relations. SSRN Journal. https://doi.org/10.2139/ssrn.4607100
[37]
Adeyemi, T.S. (2024) Defect Detection in Manufacturing: An Integrated Deep Learning Approach. Journal of Computer and Communications, 12, 153-176. https://doi.org/10.4236/jcc.2024.1210011
[38]
Janiesch, C., Zschech, P. and Heinrich, K. (2021) Machine Learning and Deep Learning. Electronic Markets, 31, 685-695. https://doi.org/10.1007/s12525-021-00475-2
[39]
Tufail, S., Riggs, H., Tariq, M. and Sarwat, A.I. (2023) Advancements and Challenges in Machine Learning: A Comprehensive Review of Models, Libraries, Applications, and Algorithms. Electronics, 12, Article 1789. https://doi.org/10.3390/electronics12081789
[40]
Kravets, P., Pasichnyk, V. and Prodaniuk, M. (2024) Mathematical Model of Logistic Regression for Binary Classification. Part 1. Regression Models of Data Generalization. VìsnikNacìonal’nogounìversitetu “L’vìvs’kapolìtehnìka”. SerìâÌnformacìjnìsistemi ta merežì, 15, 290-321. https://doi.org/10.23939/sisn2024.15.290
[41]
Zaidi, A. and Al Luhayb, A.S.M. (2023) Two Statistical Approaches to Justify the Use of the Logistic Function in Binary Logistic Regression. Mathematical Problems in Engineering, 2023, Article ID: 5525675. https://doi.org/10.1155/2023/5525675
[42]
Sun, Y., Zhang, Z., Yang, Z. and Li, D. (2019) Application of Logistic Regression with Fixed Memory Step Gradient Descent Method in Multi-Class Classification Problem. 2019 6th International Conference on Systems and Informatics (ICSAI), Shanghai, 2-4 November 2019, 516-521. https://doi.org/10.1109/icsai48974.2019.9010220
[43]
Kumar, N.A., Jangale, L., Sathe, V., Shelke, A. and Redij, T. (2024) Study of Supervised Logistic Regression Algorithm. Alochana Journal, 13, 227-230.
[44]
Ganiyu, A., Darvishi, I., Addo-Quaye, R., Yeboah-Ofori, A., Asare, B.T. and Oguntoyinbo, O. (2024) Classification Algorithms Using Ensemble Methods. 2024 11th International Conference on Future Internet of Things and Cloud (FiCloud), Vienna, 19-21 August 2024, 168-175. https://doi.org/10.1109/ficloud62933.2024.00033
[45]
Salman, H.A., Kalakech, A. and Steiti, A. (2024) Random Forest Algorithm Overview. Babylonian Journal of Machine Learning, 2024, 69-79. https://doi.org/10.58496/bjml/2024/007
[46]
Thomas, N.S. and Kaliraj, S. (2024) An Improved and Optimized Random Forest Based Approach to Predict the Software Faults. SN Computer Science, 5, Article No. 530. https://doi.org/10.1007/s42979-024-02764-x
[47]
Natras, R., Soja, B. and Schmidt, M. (2022) Ensemble Machine Learning of Random Forest, AdaBoost and XGBoost for Vertical Total Electron Content Forecasting. Remote Sensing, 14, Article 3547. https://doi.org/10.3390/rs14153547
[48]
Sahin, E.K. (2020) Assessing the Predictive Capability of Ensemble Tree Methods for Landslide Susceptibility Mapping Using XGBoost, Gradient Boosting Machine, and Random Forest. SN Applied Sciences, 2, Article No. 1308. https://doi.org/10.1007/s42452-020-3060-1
[49]
Velarde, G., Sudhir, A., Deshmane, S., Deshmukh, A., Sharma, K. and Joshi, V. (2023) Evaluating XGBoost for Balanced and Imbalanced Data: Application to Fraud Detection. arXiv: 2303.15218. https://doi.org/10.48550/arXiv.2303.15218
[50]
Khan, A.A., Chaudhari, O. and Chandra, R. (2024) A Review of Ensemble Learning and Data Augmentation Models for Class Imbalanced Problems: Combination, Implementation and Evaluation. Expert Systems with Applications, 244, Article ID: 122778. https://doi.org/10.1016/j.eswa.2023.122778
[51]
Dong, C., Xie, K., Sun, X., Lyu, M. and Yue, H. (2019) Roadway Traffic Crash Prediction Using a State-Space Model Based Support Vector Regression Approach. PLOS ONE, 14, e0214866. https://doi.org/10.1371/journal.pone.0214866
[52]
Pourroostaei Ardakani, S., Liang, X., Mengistu, K.T., So, R.S., Wei, X., He, B., et al. (2023) Road Car Accident Prediction Using a Machine-Learning-Enabled Data Analysis. Sustainability, 15, Article 5939. https://doi.org/10.3390/su15075939
[53]
Ahmed, S., Hossain, M.A., Bhuiyan, M.I.I. and Ray, S.K. (2021) A Comparative Study of Machine Learning Algorithms to Predict Road Accident Severity. 2021 20th International Conference on Ubiquitous Computing and Communications (IUCC/CIT/ DSCI/SmartCNS), London, 20-22 December 2021, 390-397.
