Forecasting the KLSE index using neural networks

Abstract

Neural networks have been actively researched by computer scientists and engineers for many years. They have captured the attention of business community in recent years and potential applications of the technology have emerged, such as the application of neural networks in forecasting. In this paper, based on the rescaled range analysis, the indices of Kuala Lumpur Stock Exchange (KLSE) are predicted by the popularly used backpropagation neural network. The choice of KLSE is an interesting one, as KLSE is one of the largest stock markets in the emerging economies in terms of capitalization. Using different trading strategies, a significant paper profit can be achieved by purchasing indexed stocks in the respective proportions. The experiment shows that useful predictions can be made without the use of extensive market data or knowledge.