Comparison of Moving Average and Artificial Neural Network Modelling for the Daily Stock Market of the TASI Index Prediction
Abstract
Many statisticians and economists are intrigued by the accuracy of predictions from time series models applied to data like stock price indices. The Moving Average Autoregressive Integrated Moving Average (MA-ARIMA) is a linear model used in time series analysis. It
transforms the original data into a kth moving average before applying the classical ARIMA. MA-ARIMA includes Simple Moving Average ARIMA (SMA-ARIMA), Weighted Moving Average ARIMA (WMA-ARIMA), and Exponential Weighted Moving Average ARIMA (EWMAARIMA). Recently, Artificial Neural Networks (ANN), particularly the forward propagation technique, have been explored as alternatives for forecasting. This paper compares MAARIMA and its variants with ANN using a single hidden layer feed-forward network to predict the Saudi Arabia stock market (TASI). The dataset comprises historical daily closing stock prices from January 1, 2020, to May 25, 2023, totaling 887 days. The study evaluates
the accuracy and effectiveness of both techniques. To our knowledge, this is the first comparison of MA-ARIMA and ANN for forecasting the Saudi market or any other market. Findings suggest that the 3rd WMA-ARIMA(3,1,2 model outperforms the ANN in predicting stock market trends. The article concludes that there is no significant difference between the accuracy of the MA-ARIMA and ANN methods in predicting future daily stock prices, providing valuable insights for investors and analysts.
Keywords
Full Text:
PDFDisclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.