Artificial Neural Networks and Inclusive Growth: A Customized Measurement Approach and Empirical Analysis for the MENA Region

Despite the growing importance of equitable development, existing measures of inclusive growth often rely on aggregation techniques that overlook regional structural and institutional nuances. This study addresses this gap by proposing an innovative, data-driven framework to construct a novel inclusive growth indicator. Based on tree pillars - growth and development, inclusion, and intergenerational equity and sustainability- this approach establishes a customized weighting scheme tailored to each country’s unique profile. The novel indicator is the used to investigate of the relationship between inclusive growth and key determinants, including inflation (INF), foreign direct investment (FDI), financial development (FD), and exports (EXP), in MENA region over the period 2000–2020. The findings reveal a clear tri-level performance hierarchy in the MENA region, with GCC nation’s leading in debt management and dependency ratios, while other nations remain hindered by wealth inequality and low labor productivity. Results also indicate a significant positive long-run impact of FDI, financial development, and exports, on inclusive growth, whereas inflation has a negative effect. Simulation results, specifically for Saudi Arabia, identify "Intergenerational Equity and Sustainability" as the pillar with the highest marginal return for overall growth scores. This study suggests the design of a multi-level policy framework to promote sustainable and inclusive growth across the MENA region. Policymakers should adopt country-specific optimal reform scenarios to identify the most effective intervention sequences. The policy implications suggest that governments in the MENA region should prioritize efficiency-driven investments in high-value services and technologies to maximize the impact of FDI.