|
|
 |
| |
|
|
|
Evaluating Financial Market Forecasting in Saudi Arabia Using Advanced Statistical Models |
|
|
|
PP: 191-203 |
|
|
|
doi:10.18576/jsap/140205
|
|
|
|
Author(s) |
|
|
|
Halla Elziber Elsiddeg Elemam,
Abdelgalal O I Abaker,
Sami Elsir Ahmed Mohamed,
Maha Fadlalsayed Ali Abdallah,
|
|
|
|
Abstract |
|
|
| This study employs sophisticated statistical and machine learning models to examine the forecasting performance of financial markets in the Kingdom of Saudi Arabia (KSA), with a particular emphasis on economic confidence indicators. It is imperative to comprehend the dynamics of financial markets in order to diversify the economy of the Kingdom of Saudi Arabia, as outlined in Vision 2030. The research assesses the effectiveness of a variety of forecasting models, including ARIMA and Long Short-Term Memory (LSTM), in predicting market trends that are influenced by indicators such as the Consumer Price Index (CPI) and Private Final Consumption Expenditure (PFCE). The methodology encompasses a comprehensive literature review, data acquisition from reputable sources, and a comparative analysis of model performance using statistical metrics. The results suggest that hybrid models, which combine traditional and machine learning techniques, produce superior forecasting accuracy. Consequently, these models offer valuable insights for financial analysts, investors, and policymakers to improve market stability and decision-making in a rapidly changing economic landscape. |
|
|
|
|
|
|
|
