NEURAL NETWORKS APPLIED TO STOCK MARKET FORECASTING: AN EMPIRICAL ANALYSIS

Neural networks are an artificial intelligence method for modeling complex target functions. For certain types of problems, such as learning to interpret complex real-world sensor data, artificial neural networks (ANNs) are among the most effective learning methods. During the last decade, they have been widely applied to the domain of financial time series prediction, and their importance in this field is growing. This paper aims to analyze neural networks for financial time series forecasting, specifically, their ability to predict future trends of North American, European, and Brazilian stock markets. Their accuracy is compared to that of a traditional forecasting method, generalized autoregressive conditional heteroskedasticity (GARCH). Furthermore, the best choice of network design is examined for each data sample. This paper concludes that ANNs do indeed have the capability to forecast the stock markets studied, and, if properly trained, robustness can be improved, depending on the network structure. In addition, the Ashley–Granger–Schmalancee and Morgan–Granger–Newbold tests indicate that ANNs outperform GARCH models in statistical terms.