Jordan Journal of Civil Engineering

Paper Detail

Performance of Traffic Accidents Prediction Models

Volume 17, No. 1, 2023
Received: 2022/06/05, Accepted: 2022/08/10


Hashem Al-Masaeid; Farah Khaled;


Modeling traffic accident frequency is an important issue to better understand the accident trends and the effectiveness of current traffic policies and practices in different countries. The main objective of this study is to model traffic road accidents, fatalities, and injuries in Jordan, using different modeling techniques including regression, Artificial Neural Network (ANN), and Autoregressive Integrated Moving Average (ARIMA) models, and to evaluate the impact of Covid-19 pandemic on traffic accident statistics for the year of 2020. To accomplish these objectives, traffic accidents, registered vehicles (REGV), population (POP), and economic gross domestic product (GDP) data from 1995 through 2020 were obtained from related sources in Jordan. Results of the analysis revealed that accidents, fatalities, and injuries have an increasing trend in Jordan. Also, it was found that the developed ANN models were more accurate for accidents, injuries, and fatalities prediction than ARIMA, which was also better than regression which comes in the last place in terms of its prediction power. Finally, it was concluded that strategies are undertaken by the government of Jordan to combat Covid-19; including complete and partial banning on travel, had resulted in a considerable reduction of accidents, injuries, and fatalities by about 35, 37, and 50%, respectively.


Traffic accident prediction models; Time series analysis; Artificial neural network; Regression; Covid-19 pandemic.