Forecasting the number of road accidents in Poland in 2024–2030 – a comparative analysis of classical methods, neural networks, and forecasts generated by AI systems
Journal of Civil Engineering and Transport · 16.11.2026 · 8 (3) · 139-148
DOI: 10.24136/tren.2026.009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Civil Engineering and Transport, online erschienen am 16.11.2026. Verfasst von Piotr Gorzelańczyk. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
The article presents a comparative analysis of forecasts of the number of road accidents in Poland in 2024–2030, developed using classical methods, artificial neural networks, and artificial intelligence (AI) tools. Based on historical data from 1990 to 2023, the accuracy, stability, and reliability of the forecasts were assessed using the mean absolute percentage error (MAPE) as the main evaluation metric. The results show that neural networks and exponential smoothing methods are characterized by the highest accuracy and stability of forecasts, while high-degree polynomial regression models and forecasts automatically generated by AI are characterized by greater variability and lower reliability. The forecasts indicate that the number of road accidents in Poland in the analyzed horizon is likely to remain stable at around 20,000–22,000 per year. The study emphasizes the importance of controlled modeling and conscious selection of forecasting methods in predicting road safety trends.
Zitieren
APA
Gorzelańczyk, P. (2026). Forecasting the number of road accidents in Poland in 2024–2030 – a comparative analysis of classical methods, neural networks, and forecasts generated by AI systems. Journal of Civil Engineering and Transport, 8(3), 139-148. https://doi.org/10.24136/tren.2026.009
Vancouver
Gorzelańczyk P. Forecasting the number of road accidents in Poland in 2024–2030 – a comparative analysis of classical methods, neural networks, and forecasts generated by AI systems. Journal of Civil Engineering and Transport. 2026;8(3):139-148. doi:10.24136/tren.2026.009
BibTeX
@article{Gorzelaczyk2026,
author = {Gorzelańczyk, Piotr},
title = {Forecasting the number of road accidents in Poland in 2024–2030 – a comparative analysis of classical methods, neural networks, and forecasts generated by AI systems},
journal = {Journal of Civil Engineering and Transport},
year = {2026},
volume = {8},
number = {3},
pages = {139--148},
doi = {10.24136/tren.2026.009}
}
EUVIMED