Using AI Model to Anticipate Road Accidents of Poland and Kosovo

Gezim Hoxha; Piotr Gorzelańczyk

doi:10.7250/bjrbe.2026-21.679

Using AI Model to Anticipate Road Accidents of Poland and Kosovo

Authors

Gezim Hoxha Department of Traffic and Transport, Faculty of Mechanical Engineering, University of Pristina, Pristina, Kosovo https://orcid.org/0000-0002-0486-7010
Piotr Gorzelańczyk Department of Transport, Stanislaw Staszic State University of Applied Sciences in Pila, Podchorazych 10 Street, 64-920 Pila, Poland https://orcid.org/0000-0001-9662-400X

DOI:

https://doi.org/10.7250/bjrbe.2026-21.679

Keywords:

forecasting, Kosovo, neural networks, pandemic, Poland, traffic accident

Abstract

This paper investigates the application of artificial neural networks for predicting road traffic accident counts in Poland and Kosovo. The study uses annual accident data collected for the period 2010–2023 from official statistical records provided by the Polish Police and the Kosovo Police. Forecasting procedures were carried out with multilayer perceptron (MLP) models developed in the Statistica environment. To assess the robustness of the models, two alternative dataset division schemes were employed, namely, 70%–15%–15% and 80%–10%–10% for the training, testing, and validation subsets. Forecast accuracy was measured using Mean Absolute Error (MAE) together with Mean Absolute Percentage Error (MAPE). The obtained forecasts suggest that the number of road traffic accidents in both analysed countries is likely to remain relatively stable over the 2024–2030 period. The analysis further demonstrates that a larger share of training observations contributes to improved predictive performance and lower estimation errors. Nevertheless, the relatively short time series constitutes a methodological limitation and requires careful interpretation of the forecasting results.

References

Abdullah, E., & Emam A. (2015). Traffic accidents analyzer using big data. 2015 Int. Conf. Comput. Sci. Comput. Intell. CSCI 2015, Las Vegas, USA, 392–397. https://doi.org/10.1109/CSCI.2015.187 DOI: https://doi.org/10.1109/CSCI.2015.187

Al-Madani, H. M. N. (2018). Global road fatality trends’ estimations based on country-wise microlevel data. Accident Analysis & Prevention, 111, 297–310. https://doi.org/10.1016/j.aap.2017.11.035 DOI: https://doi.org/10.1016/j.aap.2017.11.035

Arteaga, C., Paz, A. & Park, J. W. (2020). Injury severity on traffic crashes: A text mining with an interpretable machine-learning approach. Safety Science, 132, Article 104988. https://doi.org/10.1016/j.ssci.2020.104988 DOI: https://doi.org/10.1016/j.ssci.2020.104988

Bąk, I., Cheba, K., & Szczecińska, B. (2019). The statistical analysis of road traffic in cities of Poland. Transportation Research Procedia, 39, 14–23. https://doi.org/10.1016/j.trpro.2019.06.003 DOI: https://doi.org/10.1016/j.trpro.2019.06.003

Becoming Human. (2019, August 10). How Netflix uses AI, data science, and machine learning – from a product perspective. www.becominghuman.ai

Biswas, A. A., Mia, J., & Majumder, A. (2019). Forecasting the number of road accidents and casualties using Random Forest regression in the context of Bangladesh. 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kanpur, India, 1–5. https://doi.org/10.1109/ICCCNT45670.2019.8944500 DOI: https://doi.org/10.1109/ICCCNT45670.2019.8944500

Bloomfield, P. (1973). An exponential model in the spectrum of a scalar time series. Biometrika, 60(2), 217–226. https://doi.org/10.1093/biomet/60.2.217 DOI: https://doi.org/10.1093/biomet/60.2.217

Chand, A., Jayesh, S., & Bhasi, A. B. (2021). Road traffic accidents: An overview of data sources, analysis techniques and contributing factors. Materials Today: Proceedings, 47(15), 5135–5141. https://doi.org/10.1016/j.matpr.2021.05.415 DOI: https://doi.org/10.1016/j.matpr.2021.05.415

Chen, C. (2017). Analysis and forecast of traffic accident big data. ITM Web Conf., 12, Article 04029. https://doi.org/10.1051/itmconf/20171204029 DOI: https://doi.org/10.1051/itmconf/20171204029

Chudy-Laskowska, K., & Pisula, T. (2015). Forecasting the number of road accidents in Subcarpathia. Logistics, 4, 2782–2796.

Chudy-Laskowska, K., & Pisula, T. (2014). Forecast of the number of road accidents in Poland. Logistics, 6. https://doi.org/10.14513/actatechjaur.00951 DOI: https://doi.org/10.14513/actatechjaur.00951

StatSoft. (1997). Data mining techniques. StatSoft https://www.statsoft.pl/textbook/stathome_stat.html?https%3A%2F%2Fwww.statsoft.pl%2Ftextbook%2Fstdatmin.html

Dudek, G. (2013a). Exponential smoothing models for short-term power system load forecasting. Energy Market, 106(3), 14–19.

Dudek, G. (2013b). Forecasting time series with multiple seasonal cycles using neural networks with local learning. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (Eds.), Artificial Intelligence and Soft Computing. ICAISC 2013. Lecture Notes in Computer Science, vol. 7894. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38658-9_5 DOI: https://doi.org/10.1007/978-3-642-38658-9_5

Dutta, B., Barman, M. P., & Patowary, A. N. (2020). Application of Arima model for forecasting road accident deaths in India. International Journal of Agricultural and Statistical Sciences, 16(2), 607–615. https://connectjournals.com/pages/articledetails/toc032612

Fijorek, K., Mróz, K., Niedziela, K., & Fijorek, D. (2010). Forecasting electricity prices on the day-ahead market using data mining methods. Energy Market, 91(6) 46–50.

Fiszeder, P. (2009). GARCH class models in empirical financial research. Scientific Publishers of the Nicolaus Copernicus University. Torun.

Forecasting based on time series. (2022). http://pis.rezolwenta.eu.org/Materialy/PiS-W-5.pdf

Forbes. (2020, September 12). The amazing ways eBay is using Artificial Intelligence to boost business success. www.forbes.com

Gorzelanczyk, P., Pyszewska, D., Kalina, T., & Jurkovic, M. (2020). Analysis of road traffic safety in the Pila poviat. Scientific Journal of Silesian University of Technology. Series Transport, 107, 33–52. https://doi.org/10.20858/sjsutst.2020.107.3 DOI: https://doi.org/10.20858/sjsutst.2020.107.3

Gorzelańczyk, P., & Ho, J. S. (2024). Forecasting the number of road accidents in Poland by road type. Highlights of Vehicles, 2(1), 13–23. https://doi.org/10.54175/hveh2010002 DOI: https://doi.org/10.54175/hveh2010002

Helgason, A. (2016). Fractional integration methods and short time series: evidence from a simulation study. Political Analysis, 24(1), 59–68. https://doi.org/10.1093/pan/mpv026 DOI: https://doi.org/10.1093/pan/mpv026

Hoxha, G., Bixhaku, M., & Duraku, R. (2023a). Developing a new model for assessment of heavy vehicle-pedestrian collisions. The Baltic Journal of Road and Bridge Engineering, 18(3), 102–123. https://doi.org/10.7250/bjrbe.2023-18.610 DOI: https://doi.org/10.7250/bjrbe.2023-18.610

Hoxha, G., Fandaj, A., & Bajrami, X. (2023b). Quality of automatic traffic volume counting by cameras and impact on the qualitative indicators of traffic. Infrastructures, 8(3), Article 44. https://doi.org/10.3390/infrastructures8030044 DOI: https://doi.org/10.3390/infrastructures8030044

Hoxha, G., Gorzelanczyk, P., Likaj, R., Thaqi, S., & Cikaqi, F. (2025). Smart traffic management at intersections. Journal of Sustainable Construction Materials and Technologies, 10(2), Article 5. https://doi.org/10.29187/2458-973X.1187 DOI: https://doi.org/10.29187/2458-973X.1187

Kosovo Police. (2024). https://www.kosovopolice.com/

Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017). Building machines that learn and think like people. Behavioral and Brain Sciences, 40, Article e253. https://doi. org/10.1017/S0140525X16001837 DOI: https://doi.org/10.1017/S0140525X16001837

Oronowicz-Jaśkowiak, W. (2019). The application of neural networks in the work of forensic experts in child abuse cases. Advances in Psychiatry and Neurology/Postępy Psychiatrii i Neurologii, 28(4), 273–282. https://doi.org/10.5114/ppn.2019.92489 DOI: https://doi.org/10.5114/ppn.2019.92489

Sejdiu, L., Shala, F., Tollazzi, T., & Demolli, H. (2024). Analysis of traffic safety factors and their impact using machine learning algorithms. Civil Engineering Journal, 10(9). https://doi.org/10.28991/CEJ-2024-010-09-06 DOI: https://doi.org/10.28991/CEJ-2024-010-09-06

Shala, F., Demolli, H., & Sejdiu, L. (2024). The application of machine learning algorithms in predicting traffic accidents by considering weather conditions. International Review of Civil Engineering (IRECE), 15(2), 201–208. https://doi.org/10.15866/irece.v15i2.24368 DOI: https://doi.org/10.15866/irece.v15i2.24368

Statistic Road Accident. (2024). https://statystyka.policja.pl/

Statistics Poland. (2022). Statistical Yearbook of the Republic of Poland 2022. Warsaw, Poland: Statistics Poland. https://stat.gov.pl/en/topics/statistical-yearbooks/ statistical-yearbooks/statistical-yearbook-of-the-republic-of-poland-2022%2C2%2C24.html

Vilaça, M., Silva, N., & Coelho, M. C. (2017). Statistical analysis of the occurrence and severity of crashes involving vulnerable road users. Transportation Research Procedia, 27, 1113–1120. https://doi.org/10.1016/j.trpro.2017.12.068. DOI: https://doi.org/10.1016/j.trpro.2017.12.113

WBRSO. (2023). Western Balkans Road Safety Observatory. https://www.transport-community.org/wbrso/

Wu, Y. et al. (2020). Google’s neural machine translation system: bridging the gap between human and machine translation. arXiv:1609.08144. https://doi.org/10.48550/arXiv.1609.08144

Using AI Model to Anticipate Road Accidents of Poland and Kosovo

Authors

DOI:

Keywords:

Abstract

References

Downloads

Published

Issue

Section

License

How to Cite