Um estudo sobre arquitetura de redes neurais aplicado a previsão do retorno de ações brasileiras

Carregando...
Imagem de Miniatura
Data
2017-02-13
Orientador(res)
Pinto, Afonso de Campos
Título da Revista
ISSN da Revista
Título de Volume
Resumo

In this work, we present a statistical analysis about the characteristics that we intend to influence in the performance of neural networks in terms of assertiveness. We created a population for analysis and extracted the sample that had the best assertive performance. We can observe how the characteristics of this sample stand out and affect the neural networks. In addition, we make inferences about what kind of influence the different architectures have on the performance of neural networks. In the study, the prediction of the return of Brazilian stocks from the São Paulo Stock Exchange is made to measure the error committed by the different architectures of neural networks constructed.


Descrição
Área do Conhecimento