Empirical study of sukuk investment forecasting using artificial neural network base algorithm

Nurul Hila binti Zainuddin

Abstract

Accuracy estimation is an important issue in time series forecasting field, for example Islamic investment namely sukuk. In order to provide the accuracy estimation of forecasting, the statistical estimator has to be unbiased and has minimum error. In this study, the statistical estimator of moving average model is applied to forecast the sukuk series data. However, the accuracy of this model is questionable and in order to improve the accuracy, this study proposed a hybrid approach using artificial neural network (ANN) algorithm for moving average model. Noted that, the parameter of moving average is selected by considering the AIC, AICc and BIC criterion values, and the selected parameter eventually to be used as input layer of ANN algorithm. In order to examine the forecasting performance, the proposed algorithm used to calculate the 10 days ahead and 15 days ahead forecasting. Based on empirical result, it has shown that, the proposed algorithm helps to reduce the error estimation and eventually improve the forecasting of sukuk investment.

References

[1] L. Muhamad Safiih, N. Z. Hila, A. Mohd Tajuddin, P. Vigneswary, R. Mohd Noor Afiq, Z. Razak, Z., MD Suffian, K. Idham, “Improving the Performance of ANN-ARIMA Models for Predicting Water Quality in the Offshore Area of Kuala Terengganu, Terengganu, Malaysia”, Journal of Sustainability Science and Management, 2018, Vol. 13, pp. 27-37.

[2] X. Wang, F. Zhang, J. Ding, H.Kung, A. Latif, V. C. Jhonson, “Estimation of soil salt content (SSC) in the Ebinur Lake Wetland National Nature Reserve (ELWNNR), Northwest China, Based on a Bootstrap-bp Neural Network Model and Optimal Spectral Indices”, Science of The Total Environment, 2018, Vo. 615, pp. 918-930.

[3] E. M. Oliveira, F. L. C. Oliveira, “Forecasting Mid-long Term Electric Energy Consumption through Bagging ARIMA and Exponential Smoothing Methods”, Energy, 2018, Vol. 144, No.1, pp. 776-788.

[4] M. Khashei, M. Bijari, “An artificial neural network (p,d,q) model for time series forecasting”, Expert Systems with Applications, 2010, Vol. 37, pp. 479-489.

[5] M. Khashei, M. Bijari, “A New Hybrid Methodology for Nonlinear Time Series Forecasting”, Modelling and Simulation in Engineering, 2011, Vol. 2011, pp. 1-6.

[6] G. P. Zhang, “Time series forecasting using a hybrid ARIMA and neural network model”, Neurocomputing, 2003. Vol. 50, pp. 159–175.

[7] G. Zhang, B. E. Patuwo, M. Y. Hu, “Forecasting with Artificial Neural Networks: The State of the Art”, International Journal of Forecasting, 1998, Vol. 14, pp. 35–62.

[8] G. P. Zhang, “Time series forecasting using a hybrid ARIMA and neural network model”, Neurocomputing, 2003, Vol. 50, pp. 159–175.

[9] S. K. Nanda, D. P. Tripathy, S. K. Nayak, S. Mohapatra, “Prediction of Rainfall in India using Artificial Neural Network (ANN) Models”, I. J. Intelligent Systems and Applications, 2013, Vol. 12, pp. 1-22.

[10] L. Muhamad Safiih, W. A. Wan Saliha, N. Z. Hila, “Sample selection Model with Bootstrap (BPSS) Approach: Case Study of the Malaysian Population and Family Survey”, Open Journal of Statistics, 2016, Vol. 6, pp. 741-748.

[11] J. F. Heaton, “Introduction to Neural Networks for Java, Second Edition” , 2008, Publisher: Heaton Reserach, Inc (October 1, 2008).