Deep learning with small and big data of symmetric volatility information for predicting daily accuracy improvement of JKII prices

Abstract

PurposeThe purpose of this paper is to predict the daily accuracy improvement for the Jakarta Islamic Index (JKII) prices using deep learning (DL) with small and big data of symmetric volatility information.Design/methodology/approachThis paper uses the nonlinear autoregressive exogenous (NARX) neural network as the optimal DL approach for predicting daily accuracy improvement through small and big data of symmetric volatility information of the JKII based on the criteria of the highest accuracy score of testing and training. To train the neural network, this paper employs the three DL techniques, namely Levenberg–Marquardt (LM), Bayesian regularization (BR) and scaled conjugate gradient (SCG).FindingsThe experimental results show that the optimal DL technique for predicting daily accuracy improvement of the JKII prices is the LM training algorithm based on using small data which provide superior prediction accuracy to big data of symmetric volatility information. The LM technique develops the optimal network solution for the prediction process with 24 neurons in the hidden layer across a delay parameter equal to 20, which affords the best predicting accuracy based on the criteria of mean squared error (MSE) and correlation coefficient.Practical implicationsThis research would fill a literature gap by offering new operative techniques of DL to predict daily accuracy improvement and reduce the trading risk for the JKII prices based on symmetric volatility information.Originality/valueThis research is the first that predicts the daily accuracy improvement for JKII prices using DL with symmetric volatility information.

Predicting daily precision improvement of Jakarta Islamic Index in Indonesia’s Islamic stock market using big data mining

“…Because choosing this period is optimal for collecting the big balance data sheet of JKII's financial data from Investing database to use it for extracting the largest possible hidden knowledge from it, which helps to predict daily precision improvement of JKII prices using data mining. The four attributes of the symmetric volatility framework are used as inputs (CP, LP, HP and OP) based on studies on predicting stock markets indices by Nayak et al (2015), Khedr and Yaseen (2017), Vijh et al (2020), Ampomah et al (2021) and Ledhem (2022). Although the output layer comprises a single target to be predicted, which is the daily actual JKII prices.…”

“…Despite the existence of numerous studies on the prediction of conventional stock markets, to the best of the authors’ knowledge, there is a limited number of studies that focus on the prediction of the Islamic stock market using ANNs. In a recent study, Ledhem (2022) predicted the prices of the JKII using ANNs. His findings indicated that ANNs are highly suitable for predicting stock market prices.…”

“…As stated by Irsalinda et al (2020) and Ledhem (2022), there is an absence of newer statistical methodology in Indonesia's Islamic stock markets, especially in predicting JKII price volatility, and because the JKII was experiencing volatility and unstable behavior, investors were forced to use modern techniques such as data mining, DL, AI and ML in JM2 19,3 predicting JKII price movements. Consequently, as an expansion of the research of Irsalinda et al (2020) and Ledhem (2022), which focuses only on using artificial neural networks (ANNs) in the Islamic capital market of Indonesia, this research aims to use other efficient techniques of data mining for predicting daily precision improvement of JKII price movements and to assist investors in achieving their investment objectives and making precise investment decisions in the Islamic stock markets.…”

“…According to Aslam et al (2021), the use of data mining techniques and other new technologies like AI, deep learning (DL) and machine learning (ML) in predicting the trends of Islamic stock markets has become critical for investors to make appropriate investment choices, particularly for the Jakarta Islamic Index (JKII) in Indonesia’ Islamic stock market, which has experienced high volatility and unsteady movements (Irsalinda et al , 2020; Ledhem, 2022).…”

“…In terms of volatility, nevertheless, Ben Rejeb and Arfaoui (2019) showed that Islamic stock indexes are much more volatile than their other standard counterparts. Because this study is concentrating on the element of volatility in the JKII index, Irsalinda et al (2020) and Ledhem (2022) show that the JKII index is extremely volatile and has seen unbalanced trends.…”