Prediction of Ship Departure Delay Using Supervised Learning

The loading and unloading activities of a ship start from the activities of the ship berthing until the ship departs from the wharf. The arrival of ships to the wharf of a terminal has been scheduled or known as a window, but in reality there are still many delays in ship departure which result in an increase in the length of the ship berth so that it affects the low value of Box/Ship/Hour (BSH), and can result in the schedule of the next ship's schedule experiencing a delay berthing. This affects the income of a terminal and becomes the focus of attention for the terminal to be handled. This study was conducted to predict ship departure delay in the hope that it can help provide consideration to the terminal in compiling the next ship berthing schedule and the operational department can carry out anticipatory activities to prevent ship departure delay from ships that are predicted to be delayed through the allocation of loading and unloading facilities. The research was conducted by comparing several supervised learning methods, including the K-Nearest Neighbor (KNN), Naïve Bayes Classifier (NBC), NBC with Bagging Ensemble Classifier, Decision Tree, and Ordinal Logistic Regression. It was found that the best classification result is the KNN method (k = 5) with an accuracy value of 91%, but for the delay ≤ 4 hours and > 4 hours it has a sensitivity value ≤ 50%, it means that ships with a delay ≤ 4 hours and > 4 hours have have less accurate predictions, and the use of the bagging method on the NBC method is proven to improve the classification performance of the NBC method.