Resumo:
Prediction is concerned with using the knowledge of present and past events to make calculated estimates of future events. This is particularly important in Economy, field where we have a dynamic system that inherits nonlinearity through long term trends, seasonal patterns, cyclical movements and irregular factors.
In today’s business fields, Artificial Neural Networks (ANN) are becoming increasingly popular acting as a tool of prime importance in helping interpret the market. Many neural-net systems have been shown to work well in identifying intricate patterns, learning from experience, reaching some conclusion and making prediction.
The main goal of this work is to show the characteristics of neural networks and discuss the feasibility of neural-net applications in business fields, particularly agrobusiness, making predictions of commodities prices and comparing them with results obtained using a traditional statistical method.
