Purpose: This article maps the scholarly conversation on two important topics in the field of economic development: human capital and special economic zones. While these have been studied separately, little work is available on their intersection. Design/methodology/approach: The article is a systematic literature review. It followed the preferred reporting items for systematic review and meta-analysis (PRISMA) criteria. Findings: While human capital development has been largely discussed from the perspective of developed countries, it hasn’t been examined specifically in connection to SEZs. Moreover, there is solid evidence of the positive impact of industrial clusters, suggesting that SEZs that pursue the formation of industrial clusters might have the strongest effect on human capital development. The piece argues the intersection of human development and SEZ establishment is currently a gap in the literature calling for further empirical investigation Originality: The literature review is brought to bear on the experience of the Emirate of Dubai, in order to highlight features of its development history that make it an ideal case study for empirical investigation.
9 July 2026 in VFAST Transactions on Software Engineering
The latest developments in the Artificial Intelligence (AI) and the information management have allowed organizations to use the data on the workforce to make decisions that are predictive and strategic. Nevertheless, transforming heterogeneous and unbalanced Human Resource (HR) data into practical and understandable insights is an important engineering issue. The proposed research presents the Hybrid Strategic Workforce Analytics (H-SWA) framework, which combines a CatBoost-based classifier, class-imbalance handling, decision-threshold optimization, and SHAP-based explainable artificial intelligence for employee attrition prediction. The proposed framework is compared with Logistic Regression, Random Forest, and XGBoost models using the publicly available IBM HR Analytics Attrition dataset under the same experimental conditions. The findings indicate that H-SWA provides competitive performance across complementary evaluation measures. From an engineering perspective, the proposed framework provides an interpretable, scalable, and reproducible decision-support pipeline that is well suited to real-world HR applications involving highly imbalanced data, categorical features, and the need for transparent predictive insights. The H-SWA architecture provides a practical framework for deploying explainable workforce analytics systems and supports responsible AI-based HR decision-making.