Previsão do preço do café utilizando redes neurais

Abstract

The present article aims to develop a study on the functioning of Multi-Layer Neural Networks, in order to predict the price of coffee, based on certain climatic conditions. In this way, it can be used as an aid tool at the time of selling the culture. The product whose price will be set is defined as Arabica coffee in a 60kg bag. For the accomplishment of this project, a database was used that contains climatic factors related to the years 2003 to 2008 and the prices related to certain dates. To carry out this project, a linear regression multilayer neural network was implemented. From this, a database was trained with some characteristics related to time, which can influence the price of a bag of coffee. By the end of the article, the reader will not only have knowledge about the theory behind neural networks, but also a theoretical background on the practical use of multi-layer Neural Networks in order to predict the price of a 60kg bag of coffee.