Publication date: 03/08/2018

Namesort descending Role

Examining board:

Namesort descending Role

Summary: 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.

Access to document

Acesso à informação
Transparência Pública

© 2013 Universidade Federal do Espírito Santo. Todos os direitos reservados.
Av. Fernando Ferrari, 514 - Goiabeiras, Vitória - ES | CEP 29075-910