Using multi-agents to predict the stock market evolution based on fundamentalist analysis and fuzzy-neural networks

  • Authors:

  • Renato De C. T. Raposo;Adriano J. De O. Cruz;Sueli Mendes;Fabiano Clapp Da Silva;Fabio Mello Guimaraes De Costa;Jeferson Martins Farias;Peter Santos Andrade Silva;Armando Luiz;William Osvaldo Do Nascimento

  • Affiliations:

  • Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil;Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil;Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil;Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil;Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil;Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil;Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil;Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil;Núcleo de Computaçao Eletrônica, Instituto de Matemática, Federal University of Rio de Janeiro and Estácio de Sá University, Rio de Janeiro, RJ, Brazil

  • Venue:
  • AIC'05 Proceedings of the 5th WSEAS International Conference on Applied Informatics and Communications
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this article, we discuss the implementation of an Interactive Intelligent Decision System with emphasis on the multi-agent module. The system uses techniques of Distributed Artificial Intelligence, more specifically it adopts the cognitive multi-agent systems approach, requiring rule-based programming and human/computer interaction. The multi-agents were implemented using Java. Other purposes of this paper are: i) discuss how information obtained from users and from the market is dynamically processed and stored on a database, making all the process very adaptive; ii) show how to use the previous knowledge of economic analysts and how to represent this knowledge using frames and Common Lisp; iii) discuss the application of a combination of Neural Networks and Fuzzy Logic to predict the evolution of stock prices of Brazilian companies traded on the São Paulo Stock Exchange; iv) present the obtained results. The network indicates if a trader would have to keep, sell or buy a stock using a combination of information extracted from balance sheets (released every three months) and market indicators. The results show that the network combining the previous knowledge of the economic analyst and other economic indicators can deliver good results depending on the quality of the available data.