Forecasting Islamic securities index using artificial neural networks: performance evaluation of technical indicators. Issue 2 (10th September 2020)

• Record Type: Journal Article
• Authors: Aslam, Faheem; Mughal, Khurrum S.; Ali, Ashiq; Mohmand, Yasir Tariq
• Is Part Of: Journal of economic and administrative sciences. Volume 37:Issue 2(2021)
• Page Start: 253
• Page End: 271
• Publication Date: 2020-09-10
• Subjects: Islamic securities -- KMI-30 -- Forecasting -- Machine learning -- Neural networks -- Pakistan; Industrial management -- Periodicals; Economics -- Periodicals; Industrial management -- Arab countries -- Periodicals; Economics -- Arab countries -- Periodicals; 330.05
• DOI: 10.1108/JEAS-04-2020-0038
• Languages: English
• ISSNs: 1026-4116

Abstract

Abstract : Purpose: The purpose of this study is to develop a precise Islamic securities index forecasting model using artificial neural networks (ANNs). Design/methodology/approach: The data of daily closing prices of KMI-30 index span from Aug-2009 to Oct-2019. The data of 2, 520 observations are divided into training and test data sets by using the 80:20 ratio, which corresponds to 2016 and 504 observations, respectively. In total, 25 features are used; however, in model selection step, based on maximum accuracy, top ten indicators are selected from several iterations of predictive models. Findings: The results of feature selection show that top five influencing indicators on Islamic index include Bollinger Bands, Williams Accumulation Distribution, Aroon Oscillator, Directional Movement and Forecast Oscillator while Mesa Sine Wave is the least important. The findings show that the model captures much of the trend and some of the undulations of the original series. Practical implications: The findings of this study may have important implications for investment and risk management by using index-based products. Originality/value: Numerous studies proved that traditional econometric techniques face significant challenges in out-of-sample predictability due to model uncertainty and parameter instability. Recent studies show an upsurge of interest in machine learning algorithms to improve the prediction accuracy.