Trust region algorithms and neural networks for financial forecasting

Abstract

This thesis presents a study of using artificial neural networks in predicting stock index increments. The data of five major stock exchange indices, DAX, DJIA, FTSE-100, HSI and NASDAQ, are applied to test our network model. Unlike other financial forecasting models, our model directly uses the component stocks of the index as inputs for the prediction. For the neural network training, a trust region dogleg path algorithm is applied. For comparison purposes, other neural network training algorithms are also considered, in particular, optimization techniques with line searches are applied for solving the same class of problems. Computational results from five different financial markets show that the trust region based neural network model obtained better results compared with the results obtained by other neural networks. In particular, we show that our model is able to forecast the sign of the index increments with an average success rate above 60% in all the five stock markets. Furthermore, the best prediction result in our applications reaches the accuracy rate of 74%. Another major contribution of the thesis is the development of artificial neural network models, including component-based input selection, internal architecture and preprocessing of the sample data. Based on individual and interactive sensitivity analysis on the three major factors in network modeling, our results generalize some valuable recommendations on neural network constructions.