Predicting Direction of Stock Prices Index Movement Using Artificial Neural Networks: The Case of Libyan Financial Market

Abstract

Aims: The aim of this paper is to present techniques indicators of artificial neural networks (ANNs) model using for predicting the exact movements of stock price in the daily Libyan Stock Market (LSM) index forecasting. Study Design: Research paper. Place and Duration of Study: Libyan stock market from January 2, 2007 to March 28, 2013.  Methodology: The data from an emerging market Libyan Stock Market are applied as a case study. Twelve technical indicators were selected as inputs of the proposed models. The forecasting ability of the ANN model is accessed using back-propagation neural network of errors such as MAE, RMSE, MAPE and R2. Two comprehensive parameter setting experiments for both the technical indicators and the levels of the index in the market were performed to improve their prediction performances. Results: The experimental statistical results show that the ANN model accurately predicted the direction of movement with the average prediction rate 91% of data analysis in its best case, which is a perfectly good outcome. The relationship strength between parameter combination and forecast accuracy measures such as MAE, MAPE, and RMSE is strong (R2≥0.99). The statistical and financial performance of this technique is evaluated and empirical results revealed that artificial neural networks can be used as a better alternative technique for forecasting the daily stock market prices. Conclusion: This study proved the significance of using twelve particular technical market indicators which gave also useful results in predicting the direction of stock price movement. To improve ANN model capabilities, a mixture of technical and fundamental factors as inputs over different time period were used to be an effective tool in forecasting the market level and direction.