Graded forecasting using an array of bipolar predictions: application of probabilistic neural networks to a stock market index

Abstract

To an increasing extent over the past decade, software learning methods including neural networks have been used for prediction in financial markets and other areas. By far the most popular type of neural network has been backpropagation. However, the advantages of other learning techniques such as the swift response of the probabilistic neural network (PNN) suggest the desirability of adapting other models to the predictive function. Unfortunately, the conventional architecture for probabilistic neural networks yields only a bipolar output corresponding to Yes or No; Up or Down. This limitation may be circumvented in part by using a graded forecast of multiple discrete values. More specifically, the approach involves an architecture comprising an array of elementary PNNs with bipolar output. This paper explores a number of interrelated topics: (1) presentation of a new architecture for graded forecasting using an arrayed probabilistic network (APN); (2) use of a “mistake chart” to compare the accuracy of learning systems against default performance based on a constant prediction; and (3) evaluation of several backpropagation models against a recurrent neural network (RNN) as well as PNN, APN, and case based reasoning. These concepts are investigated against the backdrop of a practical application involving the prediction of a stock market index.