PREDIÇÃO DO PREÇO DA ARROBA DO BOI UTILIZANDO REDES NEURAIS ARTIFICIAIS

• Ano de defesa: 2021
• Autor(a) principal: Felipe Ferraz de Souza
• Orientador(a): Andrea Teresa Riccio Barbosa
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Fundação Universidade Federal de Mato Grosso do Sul
• País: Brasil
• Palavras-chave em Português: preço arroba de boi, predição de valor, inteligência artificial
• Link de acesso: https://repositorio.ufms.br/handle/123456789/4379

In this paper, a model for predicting the price of live cattle with reference to the price provided by CEPEA is proposed. This prediction is made based on the combination of variables that interfere in the composition of the indicator, such as the dollar value and the corn value. After identifying the variables that have the greatest influence on the composition of the price, to implement the model, Artificial Neural Networks of the MLP (Multilayer Perceptron) type were used. The simulation of the MLP network was used free software Weka (Waikato Environment for Knowledge Analysis) and several simulations were performed with different configurations, both in the number of variables and in the configuration of the network model. During the execution of the tests, it was decided to adopt the model that presented the best result and with the network configuration having the fewest possible variables. Some tests the network reached below 4% error rate. Therefore, the architecture and parameters of the network are more suitable for predicting the price of the cattle's.