Prediction of stock market prices using neural network techniques

Abstract

Issuing stocks is the key method to raise money for corporations. Today, stocks have become the most important financial instruments. Currently, there are several methods by which one can predict financial markets, but none of them is quite accurate. After introducing same basic concepts and the history of stocks, this work continues to introduce some typical fundamental and technical analysis methods already developed by economists, and then presents a relatively new system to forecast the stack market using revised Back Propagation (BP) algorithms. The system exploits BP neural networks to help find the correlation between stock price and the affecting factors hidden behind the financial market. The topology is a typical three-layer neural network with one input layer, one hidden layer and one output layer. The supervised algorithms are the Feed-forward, Cascade-forward, and Elman BP. They are trained respectively by seven BP techniques: the Gradient Descent BP, the Gradient Descent With Momentum BP, the Gradient Descent With Adaptive Learning Rate BP, the Gradient Descent With Momentum & Adaptive Learning Rate BP, the Levenberg-Marquardt BP, the Broyden-Fletcher-Goldfarb-Shanno (BFGS) Quasi-Newton, and the Resilient Propagation (RPROP) BP. Data used to train and test the neural networks involve the Shanghai Stock Exchange Composite Index, and the Shenzhen Stock Exchange Component Index.