Russian Federation
Voronezh, Russian Federation
This paper presents a comprehensive methodology for the development of a predictive model for road traffic accidents (RTAs). The main focus is on the stages of multidimensional feature space formation, the justification for the choice of architecture based on the XGBoost algorithm, and the development of a model verification technique. The article provides a detailed description of a systems approach to the integration of heterogeneous data (infrastructural, meteorological, temporal) to create a highly reliable decision support system. The proposed clustering technique allows for the formalization of the process of identifying latent accident hotspots, which is a significant step in the digitalization of road safety management.
machine learning, road traffic accidents, gradient boosting, XGBoost, systems analysis, accident forecasting
1. O bezopasnosti dorozhnogo dvizheniya : Federal'nyy zakon ot 10.12.1995 № 196-FZ // Konsul'tantPlyus: [sayt]. – URL: https://www.consultant.ru/document/cons_doc_LAW_8585/ (data obrascheniya: 05.02.2026).
2. GOST R 50597-2017. Dorogi avtomobil'nye i ulicy. Trebovaniya k ekspluatacionnomu sostoyaniyu, dopustimomu po usloviyam obespecheniya bezopasnosti dorozhnogo dvizheniya. Metody kontrolya. – Moskva : Standartinform, 2017. – 24 s.
3. Chen, T. XGBoost: A Scalable Tree Boosting System / T. Chen, C. Guestrin // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. – 2016. – P. 785–794. DOI: https://doi.org/10.1145/2939672.2939785
4. Hastie, T. The Elements of Statistical Learning : Data Mining, Inference, and Prediction / T. Hastie, R. Tibshirani, J. Friedman. – 2nd ed. – New York : Springer, 2009. – 745 p. DOI: https://doi.org/10.1007/978-0-387-84858-7
5. Pokazateli sostoyaniya bezopasnosti dorozhnogo dvizheniya : sayt. – URL: http://stat.gibdd.ru (data obrascheniya: 09.02.2026).
6. Petrov, A. I. Dorozhno-transportnaya avariynost' v Rossii / A. I. Petrov, V. I. Kolesov // Ekonomicheskie i social'nye peremeny: fakty, tendencii, prognoz. – 2021. – T. 14, № 1. – S. 199–220.
7. Sazonova, S. A. Modelirovanie processa diagnostiki utechek na osnove dvuhal'ternativnoy gipotezy s uchetom pomeh ot stohastichnosti potrebleniya v gidravlicheskoy sisteme / S. A. Sazonova // Modelirovanie sistem i processov. – 2024. – T. 17, № 1. – S. 111–120.
8. Vikulin, I. A. Imitacionnoe modelirovanie deformativnyh pokazateley vedomstvennyh avtomobil'nyh dorog / I. A. Vikulin // Modelirovanie sistem i processov. – 2024. – T. 17, № 2. – S. 24–31.
9. Korobova, L. A. Sistemnyy podhod pri reshenii prikladnyh medicinskih diagnosticheskih zadach / L. A. Korobova // Modelirovanie sistem i processov. – 2024. – T. 17, № 3. – S. 52–61.
