Journal of Statistics Applications & Probability

Author Country (or Countries)

Saudi Arabia


The present work aims to tackle the crucial objective of forecasting values for a range of financial market indices in order to maximize income while minimizing potential losses. This study utilizes a comparative analysis approach to examine the performance of artificial neural networks (ANNs) and decision tree models in predicting stock market movements in Saudi Arabia (KSA). The analysis is conducted using a daily database. The predictive models included in this study are constructed using historical stock market data, which encompasses the time period from January 1, 2013, to October 4, 2023. The primary objective of these models is to generate accurate projections specifically for the Tadawul Daily Index. The main objective of this study is to evaluate and contrast the effectiveness of artificial neural network (ANN) and decision tree models in predicting the performance of the stock market in Saudi Arabia. The analysis demonstrates that the decision tree model has a somewhat lower predictive capability when compared to the artificial neural network (ANN) model. The present study utilizes statistical metrics, namely root-mean-squared error (RMSE) and mean absolute error (MAE), to assess and quantify the accuracy of predictions. Moreover, a thorough examination is undertaken, encompassing a range of relevant statistical indicators, and visually representing the data series using graphical means. The utilization of a diverse methodology serves to augment knowledge and facilitate a comprehensive grasp of the intrinsic daily patterns observed in the Tadawul Daily Index. The objective is to enhance the understanding and examination of the complexities of the stock market, so empowering investors and financial analysts to make educated choices that match with their strategic goals and risk management methods. The studys findings provide significant contributions to the field of financial market prediction, specifically in the Kingdom of Saudi Arabia.

Digital Object Identifier (DOI)