Forecasting of Dow Jones Sukuk Index Prices Using Artificial Intelligence Systems

OpenAlex İngilizce

The objective of this paper is to predict the price of the Sukuk index using artificial intelligence models.The Dow Jones Middle East and North Africa (DJMENA) Sukuk indices and the Dow Jones Gulf Cooperation Council (DJGCC) Sukuk indices were chosen as data sets.In addition to the Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Radial Basis Function Neural Network (RBFNN) models in the literature, a new RNN-based artificial neural network model has also been developed.As a result of the research, the MAE values obtained from the DJMENA data set for LSTM, RNN, the proposed model, and RBFNN, respectively, are 0.95, 0.32, 0.22, and 1.16.The MAE values of 1.24, 0.49, 0.20, and 1.58 were obtained for the DJGCC dataset, in the same order.The best predictive performances of the model are (1) the proposed model, (2) RNN, and (3) LSTM, and the lowest performance, (4) RBFNN, respectively.The main contribution of the study is the comparison of RNN, RBF, and LSTM models in the estimation of DJMENA and DJGCC indices and the development of a new RNN-based model that provides the best performance.