Artificial intelligence-driven predictive analytics and institutional performance in Gulf financial systems: Evidence from GCC financial institutions

Type of the article: Research Article AbstractThe integration of artificial intelligence-driven predictive analytics has redefined financial management and decision-making across Gulf economies. This study compares the performance of artificial-intelligence-based and traditional predictive models using data from twenty financial institutions from six Gulf Cooperation Council countries. A quantitative cross-sectional design was adopted, and analysis of variance revealed statistically significant differences (p < 0.001) across all indicators. Predictive accuracy increased from 83.5 to 91.5 per cent (F = 4.23 × 10²⁹), operational efficiency from 12 to 19.5 per cent (F = 1.31 × 10³¹), risk-management effectiveness from 7.0 to 9.3 points (F = 2.69 × 10³⁰), and customer satisfaction from 6.5 to 8.5 points (F = 1.69 × 10³⁰). Regression analyses confirmed these outcomes: model type produced significant coefficients for predictive accuracy (β = 8.21, p < 0.001), operational efficiency (β = 7.46, p < 0.001), risk-management effectiveness (β = 2.29, p < 0.001), and customer satisfaction (β = 1.84, p < 0.001). The overall model explained 84 per cent (R² = 0.84) of the variation in institutional performance, confirming the strong predictive power of artificial-intelligence models. These results demonstrate that intelligent predictive systems significantly enhance accuracy, efficiency, and stakeholder value. The study concludes that transparent and ethically governed analytical frameworks are essential for sustainable financial competitiveness and responsible innovation in the Gulf region.