Machine Learning-Based Models for Accident Prediction at a Korean Container Port

The occurrence of accidents at container ports results in damages and economic losses the terminal operation. Therefore, it is necessary to accurately predict ports. Several machine learning models have been applied a port under various time intervals, optimal model was selected by comparing different terms their accuracy, precision, recall, F1 score. show that deep neural network gradient boosting with an interval 6 h exhibits highest performance all metrics. methods can be used predicting future.