Prediction of Container Handling Using Backpropagation Neural Network Approach

Ports are crucial nodes in the flow of trade and goods distribution, with 40% of 90% of the world's trade routes passing through Indonesia. This study explores the application of Backpropagation Neural Networks (BPNNs) in predicting container handling volumes at PT XYZ, a company specializing in international container services. Developing accurate and responsive planning to meet future needs is challenging without analyzing the trends and patterns observed in historical data. By utilizing historical data from 2019 to 2023, the research aims to forecast container handling for 2024. The BPNNs were trained and tested using various network architectures and parameters, with the model demonstrating significant accuracy in predictions. The study highlights the benefits of employing artificial neural networks over traditional statistical methods because they can model complex, non-linear relationships. The results indicate an expected increase of 15,09% in container handling volume for 2024 compared to 2023, emphasizing the model's potential as a reliable decision-support tool for operational planning in the port industry. These findings contribute to developing more efficient port management strategies, supporting better logistics and transportation planning decision-making processes.