Predicting Car Accident Severity in Northwest Ethiopia: A Machine Learning Approach Leveraging Driver, Environmental, and Road Conditions

Abstract Background Car accidents in Northwest Ethiopia have significantly increased in severity, with increasing impacts on public safety. This study aims to predict car accident severity in the region by considering driver behavior, environmental conditions, and road characteristics, utilizing machine learning models to enhance traffic safety measures. Methods This study used a dataset comprising accident records, weather conditions, road types, traffic volume, and driver characteristics. Various machine learning models, including logistic regression, decision trees, random forests, gradient boosting, XGBoost, LightGBM, support vector machines, K-nearest neighbors, multilayer perceptron (neural networks), and naive Bayes, have been employed to predict accident severity. Model performance was assessed in terms of accuracy, precision, recall, and the F1 score. Results Driver-related factors, including age and behavior, were found to significantly influence accident severity. Environmental factors, such as weather and road type, also play crucial roles in determining outcomes. Among the evaluated models, the random forest classifier demonstrated superior performance, achieving an initial accuracy of 78% in predicting fatal accidents. Its performance was improved to 82% through hyperparameter tuning, highlighting its strong predictive ability. Conclusions This research highlights the importance of environmental and driver-related factors in predicting accident severity in Northwest Ethiopia. The random forest model proves to be an effective tool for forecasting accident severity, which could inform policies and interventions to improve road safety in the region. Future work should focus on expanding the dataset and exploring additional models for better prediction accuracy.