Prediction and time-series analysis of road deaths per million inhabitants in the republic of Serbia and the European union for the period 2012 to 2030

Abstract

The number of road traffic fatalities remains a significant road safety concern in the Republic of Serbia. This study aimed to identify an appropriate forecasting model for monitoring and predicting road traffic fatalities and to assess whether the target of the Decade of Action for Road Safety 2021–2030, which aims to reduce road traffic fatalities by 50% by 2030, is likely to be achieved. Three time-series forecasting models available in MINITAB software were applied: the linear trend model, quadratic trend model, and growth model. Forecasted values were compared with observed data, and the quadratic trend model demonstrated the highest forecasting accuracy, exhibiting the lowest percentage error for the period from 2012 to 2022. Therefore, this model was selected to predict road deaths per million inhabitants in Serbia for the period from 2022 to 2030. The results indicate a substantial projected increase in road fatalities during this period, representing an unfavorable trend for road safety. A comparative analysis with the European Union showed that road deaths per million inhabitants decreased by approximately 13% in Serbia between 2012 and 2022, compared with an average decrease of approximately 15% in the EU. Overall, the findings suggest that the 2030 target is unlikely to be achieved under current trends without additional interventions and systematic safety measures.