The main aim of this paper is to use chaos methodology in an attempt to predict the Baltic Dry Indices (BDI, BCI, BPI) using the invariant parameters of the reconstructed strange attractor that governs the system’s evolution. This is the result of the new emerging field in econo-physics which mainly consists of autonomous physic-mathematical models that have been already applied to financial analysis. The proposed methodology is estimating the optimal delay time and the minimum embedding dimension with the method of False Nearest Neighbors (FNN). Monitoring the trajectories of the corresponding strange attractor we achieved a 30, 60, 90 and 120 time steps out of sample prediction.