期刊名称：International Journal of Computer Information Systems and Industrial Management Applications
印刷版ISSN：2150-7988
电子版ISSN：2150-7988
出版年度：2014
期号：6
页码：257-269
出版社：Machine Intelligence Research Labs (MIR Labs)
摘要：Forecasting the behavior of the financial market is a nontrivial task that relies on the discovery of strong empirical regularities in observations of the system. These regularities are often masked by noise and the financial time series often have nonlinear and non-stationary behavior. With the rise of artificial intelligence technology and the growing interrelated markets of the last two decades offering unprecedented trading opportunities, technical analysis simply based on forecasting models is no longer enough. To meet the trading challenge in today's global market, technical analysis must be redefined. Before using the neural network models some issues such as data preprocessing, network architecture and learning parameters are to be considered. Data normalization is a fundamental data preprocessing step for learning from data before feeding to the Artificial Neural Network (ANN). Finding an appropriate method to normalize time series data is one of the most critical steps in a data mining process. In this paper we considered two ANN models and two neuro-genetic hybrid models for forecasting the closing prices of Indian stock market. The present pursuit evaluates impact of various normalization methods on four intelligent forecasting models i.e. a simple ANN model trained with gradient descent (ANN-GD), genetic algorithm (ANN-GA), and a functional link artificial neural network model trained with GD (FLANN-GD) and genetic algorithm (FLANN-GA). The present study is applied on daily closing price of Bombay stock exchange (BSE) and several empirical as well as experimental result shows that these models can be promising tools for the Indian stock market forecasting and the prediction performance of the models are strongly influenced by the data preprocessing method used.
关键词：artificial neural networks; back propagation; ; normalization; functional link artificial neural network; gradient ; descent.
