Published Link:

Co-authored with Ioanna Atsalaki, George Atsalakis and Nektarios Michail. The paper has been published in Journal of Economics and Finance (2025): 1-28.

We propose a novel application of artificial intelligence in maritime economics by employing the Adaptive Neuro-Fuzzy Inference System (ANFIS) to forecast the Baltic Dry Index (BDI).

ANFIS combines the learning capabilities of neural networks with the interpretability of fuzzy logic, resulting in significantly more accurate forecasts compared to traditional models.

Our results demonstrate that ANFIS outperforms a feed-forward neural network, as well as AR and ARMA models, in terms of Root Mean Squared Error (RMSE), offering a valuable decision-support tool for shipping stakeholders and a new path for behavioral modeling in freight markets.