Forecasting Secondhand Tanker Price Through Wavelet Neural Networks Based on Adaptive Genetic Algorithm

Seaborne crude oil remains the main source of energy in modern world terms volume, accounting for nearly half all internationally traded oil. The shipping market is already characterized by high volatility, coupled with impact COVID-19 lockdown and geopolitics events. Price forecasting has become a necessary challenging task shipowners other stakeholders. In literature, usual focus on newbuilding ship price or freight rate. A limited number literature secondhand tanker price. On hand, there few that use wavelet neural networks based adaptive genetic algorithm (AGA-WNN) to predict market. This paper mainly studies application hybrid model prediction 5 kinds sizes. performance AGA-WNN time series 10 15 years compared basic provided six benchmark models, using three error metrics two statistical tests. We can point out provides encouraging promising results, outperforming baseline models both accuracy robustness. It be said gives best overall predictive performance.