ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. AI in Finance
This article is part of the Research TopicSmart Forecasting: Deep Learning and Explainable AI for Real-World Time Series PredictionView all 7 articles
Modelling and Forecasting Saudi Banking Stability using ARIMA and Exponential Smoothing Technique
Provisionally accepted
- 1King Faisal University, Al Ahsa, Saudi Arabia
- 2Al-Balqa Applied University Faculty of Engineering, As-Salt, Jordan
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
This research examines the key factors influencing the financial stability of Saudi banks by developing an optimal stepwise linear regression model. The research uses financial information gathered from 11 Saudi banks over the period 2014-2021. Six categories for key performance indicators (KPIs) which consist of profitability, liquidity, asset quality, capitalization, bank size and economic growth are included in the model. The Z-score is used as its dependent variable for all stability measures. A model with the lowest standard error should be selected as the best explanatory model among all options while also maintaining the highest adjusted R-squared value. The findings showed that the chosen model has the lowest standard error around (7.209) and the highest adjusted R-squared (71.3%), The study demonstrates that NII1 ratio and CAR statistics alongside bank asset size (log of assets) produce positive effects on stability yet the stability declines when banks use investment ratio statistics or loan impairment ratio indicators. Economic growth (GDP) shows no significant influence. The second phase of this research uses ARIMA and exponential smoothing models which are selected to produce Z-score predictions through 2030. The chosen forecast validation metrics include RMSE, MAE, MAPE and E-square. The standardized forecasts enable banks to compare resulting data with each other. The financial performance data shows different trends. Studies indicate that Arab National Bank and National Commercial Bank will provide consistent financial outcomes. Saudi Investment Bank and Bank Al - Jazira have moderate trends with high forecast precision. Al Rajhi Bank, Samba Financial Group and Saudi British Bank continue to operate steadily. The empirical findings offer support to stakeholders and regulatory authorities in decision-making processes that enable alignment with the Vision 2030 objectives.
Keywords: ARIMA models, Asset quality, Banks' Wealth, capitalization, economic growth, Forecasting models, Liquidity, profitability
Received: 09 Sep 2025; Accepted: 20 Jan 2026.
Copyright: © 2026 Alnajjar, Assous and ALnajjar. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Hamzeh Assous
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.