Computer applications in the context of financial speculation

In this paper we analyze the issues related to computer applications in finance. In particular, in Chapter 2 we deal with the particular financial market named FOREX and how well suited computational tools as Artificial Neural Networks (detailed in Chapter 1) can cope with the forecasting problem. In fact, ANNs methods have become very important in making (financial) predictions and for solving business problems, where they have proven their advantages over statistical and other traditional methods. These tools are most implemented in forecasting stock prices, returns, and stock modeling, and the most frequent methodology is the Backpropagation algorithm. In spite of many benefits, there are also limitations that should be investigated, such as the relevance of the results, and the “best” topology for the certain problems. The development of decision models using IT solutions implementing neural network techniques allows today to face many (non-linear) problems, although not showing the quantitative relationship between cause and effect in the markets. In Chapter 3 we illustrate the main issues related to the development of such models and the (computer) application of ANNs to the prediction of financial markets.