• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Doctoral Thesis
DOI
https://doi.org/10.11606/T.12.2004.tde-29042024-142911
Document
Author
Full name
Rodrigo Octávio Marques de Almeida
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2004
Supervisor
Committee
Fava, Vera Lucia (President)
Diaz, Maria Dolores Montoya
Francisco, Gerson
Rosenfeld, Rogério
Santos, Jose Carlos de Souza
Title in Portuguese
Três ensaios com aplicações de redes neurais em séries financeiras
Keywords in Portuguese
Finanças
Mercado financeiro
Redes neurais
Abstract in Portuguese
A Hipótese da Eficiência de Mercados (HEM) postula que os preços dos ativos nos mercados financeiros devem refletir toda a informação disponível: como consequência, os preços devem ser consistentes com seus fundamentos. Esta tese examina a evidência empírica da HEM usando a abordagem das redes neurais. Muitos estudos têm mostrado que redes neurais artificiais têm a capacidade de aprender a mecânica dos mercados acionários. A tese está dividida em três ensaios. O primeiro ensaio aplica os modelos de redes neurais para prever os três principais mercados acionários latino-americanos (Brasil, Argentina e México). O ensaio dois, foca o papel da análise técnica na sinalização dos pontos de entrada e saída do mercado. O ensaio três, extende os ensaios um e dois e aplica as redes recorrentes e de saltos de conexão. Os três ensaios concluem que as redes neurais são uma boa ferramenta para o market timing da alocação de ativos
Title in English
Three essays with applications of neural networks in financial series
Keywords in English
Finance
Financial market
Neural networks
Abstract in English
The Efficient Market Hypothesis (EMH) states that asset prices in financial markets should reflect all available Information: as consequence, price should always be consistent with "fundamentals". In this dissertation, we examine the empirical evidence of EMH using a neural network approach. Many studies have shown that the artificial neural networks have the capability to learn the underlying mechanics of stock markets. The dissertation is divided in three essays. First essay applies neural network models to predict the three main stock markets in Latin America (Brazil, Argentina and México) Essay two focuses on the role of technical analysis in signaling the timing of stock market entry and exit. Essay three extends essays one and two and applies both recurrent and jump connections networks. The three essays conclude that neural networks are a good tool to market timing asset allocation
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2024-04-29
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.