Ensemble system based on genetic algorithm for stock market forecasting

Financial time series forecasting is regarded as one of the most challenging applications of time series forecasting. Many researchers have been focusing on this topic due to the potential of yielding significant profits on the invested money in a short time frame. Believing in the predictability of stock markets, traders have been using Technical Analysis tools for a very long time to analyze and predict the behavior of stocks, aiming to make the best investment decisions possible with this information. In addition, applying machine learning techniques to predict stock market movements has become an area of research that has received a lot of attention in recent years. Popular algorithms such as Artificial Neural Networks and Support Vector Machines have been widely used in this area and they have been reporting satisfactory performances. As an attempt to improve the accuracy of these algorithms, researchers have been proposing techniques to combine them, forming Ensemble Systems. This work presents the design of an Ensemble System based on Genetic Algorithm for forecasting the weekly prices' trend in the Sao Paulo Stock Exchange Index (Ibovespa Index). In order to evaluate the performance of the proposed method, experiments were conducted to compare it with other popular ensemble methods (e.g., Bagging, Boosting and Random Forests). Finally, the empirical results show that the proposed model outperforms the other ensemble methods. Therefore, this implies that the proposed approach can be used by traders as a promising tool for forecasting stock market prices.