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 challenging problem. In this work, every day the stocks are ranked by technique for order preference by similarity to ideal solution (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 improve the selection, another method should be used. So, a hybrid model composed of empirical mode decomposition (EMD) and extreme learning machine (ELM) is proposed. The EMD decomposes the series into several sub-series, and thus the main omponent (trend) 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. The method was applied in a universe of 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.

In the brazilian stock market, there are dozens of stocks which the investor can invest.However, for short-term investments, to analyze all those stocks and decide which one to buy is a hard task.So, many investors operate with a small set of stocks.In order to deal with this situation, the technique for order preference by similarity to ideal solution (TOPSIS) was used to treat several alternatives simultaneously and to rank the most suitable, according to the criteria provided by the technical analysis in the form of indicators.In this paper the technique was applied to select the stocks to be purchased each day.The results were evaluated in terms of percentage of selection with profit and percentage of return.The selection made by TOPSIS achieved a return higher then the Bovespa index and random selection.

The use of models that combine empirical mode decomposition (EMD) and artificial neural networks (ANN) to time series prediction has been attracted much research interest in several areas of great relevance. However, the way the two methods are combined can vary. Thus, a comparison between different combinations of models is presented in this work. The first objective is to verify if the use of EMD improves the prediction results. The second objective is to compare whether it is better to group the intrinsic mode function (IMFs) and then perform the prediction, or predict each IMF separately and then aggregate the results. The methods were tested for six different time series and the results show that EMD improves the prediction for the most of the investigated series, especially if one predictor is used for each IMF separately.