Desenvolvimento de um método híbrido para negociações de ações na bolsa de valores brasileira

• Ano de defesa: 2018
• Autor(a) principal: Ebermam, Elivelto
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; BR; Mestrado em Informática; Centro Tecnológico; UFES; Programa de Pós-Graduação em Informática
• Palavras-chave em Português: TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution); Stock trading; Technical analysis; Empirical mode decomposition (EMD); Extreme learning machine (ELM); Decomposição de modo empírico (EMD); Máquinas de aprendizado extremo (ELM); Negociação de ações; Análise técnica; Técnica para preferência de ordem por similaridade à solução ideal (TOPSIS); Ações (Finanças) - Negociação; Bolsa de valores; Análise técnica (Análise de investimentos); Ciência da Computação; 004
• Link de acesso: http://repositorio.ufes.br/handle/10/10725

The Brazilian stock market has attracted many investors and moves billions of Real daily. However, deciding when to buy or sell a stock is not an easy task because the market is hard to predict, being influenced by political and economic factors. Thus, methodologies based on computational intelligence have been applied to this task. However, most papers select an a priori stock or index to the application of a given method. The stock selection itself is already a challenging problem, since each market has several stocks. Thus, a multicriteria decision-making method such as the technique for order preference by similarity to ideal solution (TOPSIS) can be applied. In this work, every day the stocks are ranked by TOPSIS using technical analysis criteria, and the most suitable stock is selected for purchase. Even so, it may occur that the market is not favorable to purchase on certain days, or even, the TOPSIS make an incorrect selection.To increase the reliability of the selection, another method should be used. Thus, a hybrid model composed of empirical mode decomposition (EMD) and extreme learning machine (ELM) is used. The EMD decomposes the series into several sub-series, and thus the main (trend) component is extracted. This component is processed by the ELM, which performs the prediction of the next element of component. If the value predicted by the ELM is greater than the last value, then the purchase of the stock is confirmed. A second confirmation of the purchase can be made by negotiation rules of technical indicators. Individual indicators and combinations between two indicators were tested. The method was applied to 50 stocks in the Brazilian market. The selection made by TOPSIS showed promising results when compared to the random selection and the return generated by the Bovespa index. Confirmation with the EMD-ELM hybrid model was able to increase the percentage of profit tradings.