Machine Learning-Based Regression Models for Price Prediction in the Australian Container Shipping Industry: Case Study of Asia-Oceania Trade Lane

The objective of this paper is to train a data-driven price prediction model for container pricing based on demand and supply for the Australian container shipping industry. The sourcing of demand, supply and pricing data has been done from Australian ports, Sea-Intelligence maritime analysis and the Shanghai Freight Index (SCFI) respectively. Data-driven prediction have been realized by applying three different regression models that include support vector regression (SVR), random forest regression (RFR) and gradient booster regression (GBR) over the gathered datasets after initial feature engineering. A comparison of research outcomes shows that GBR outperforms all the other models by offering a test accuracy of 84%