PREDICTING NEXT TRADING DAY CLOSING PRICE OF QATAR EXCHANGE INDEX USING TECHNICAL INDICATORS AND ARTIFICIAL NEURAL NETWORKS

• Author: Farzaneh Amani,Adam Fadlalla
• Date: 01 October 2014
• DOI: http://doi.org/10.1002/isaf.1358
• Published date: 01 October 2014

PREDICTING NEXT TRADING DAY CLOSING PRICE OF QATAR

EXCHANGE INDEX USING TECHNICAL INDICATORS AND

ARTIFICIAL NEURAL NETWORKS

ADAM FADLALLA*AND FARZANEH AMANI

Department of Accounting and Information Systems, Qatar University, Doha, Qatar

SUMMARY

Accurate prediction of stock market price is of great importance to many stakeholders. Artificial neural networks

(ANNs) have shown robust capability in predicting stock price return, future stock price and the direction of stock

market movement. The major aim of this study is to predict the next trading day closing price of the Qatar

Exchange (QE) Index using historical data from 3 January 2010 to 31 December 2012. A multilayer perceptron

ANN architecture was used as a prediction model with 10 market technical indicators as input variables. The

experimental results indicate that ANNs are an effective modelling technique for predicting the QE Index with high

accuracy, outperforming the well-established autoregressive integrated moving average models. To the best of our

knowledge, this is the first attempt to use ANNs to predict the QE Index, and its performance results are

comparable to, and sometimes better than, many stock market predictions reported in the literature. The ANN

model also revealed that the weighted and simple moving averages are the most important technical indicators in

predicting the QE Index, and the accumulation/distribution oscillator is the least important such indicator. The

analysis results also indicated that the ANNs are resilient to stock market volatility. Copyright © 2014 John Wiley

& Sons, Ltd.

Keywords: technical indicators; artificial neural networks (ANNs); multilayer perceptron (MLP); autoregressive

integrated moving average (ARIMA), Qatar Exchange (QE) Index; predicting closing price

1. INTRODUCTION

Prediction of stock markets is extremely challenging. Stock markets are characterized by complexity,

nonlinearity, subtleties and hard-to-comprehend interactions (Bahrammirzaee, 2010). In addition, stock

markets are influenced by macro factors such as ‘political events, company’s policies, general economic

conditions, commodity price index, bank rates, investors’expectations, institutional investors’choices,

and psychological factors of investors’(Wang et al., 2011). However, accurately predicting a stock

market is of great interest to many stakeholders; for instance, investors depend on a stock market’s

forecasting to make a profit and guard their investments against risks; government agencies use it to

monitor market fluctuations; and researchers use it as a benchmark for studying financial issues, such

as portfolio selection and pricing of financial derivatives. Furthermore, financial firms and private

investors depend greatly on stock index forecasting as a major activity when making investment

decisions (Lu and Wu, 2011), when developing effective market trading strategies (Leung et al.,

2000), and when identifying market opportunities and challenges (Enke et al., 2011).

* Cor respondence to: Adam Fadlalla, Department of Accounting and Information Systems, Qatar University, Doha, Qatar.

E-mail: fadlalla@qu.edu.qa

Copyright © 2014 John Wiley & Sons, Ltd.

INTELLIGENT SYSTEMS IN ACCOUNTING, FINANCE AND MANAGEMENT

Intell. Sys. Acc. Fin. Mgmt. 21, 209–223 (2014)

Published online 2 August 2014 in Wiley Online Library (wileyonlinelibrary.com)DOI: 10.1002/isaf.1358