QUANTITATIVE MODELING OF WORKFORCE FORECASTING USING SQL-DRIVEN DATA PIPELINES AND POWER BI DASHBOARDS IN PREDICTIVE HR ANALYTICS

Abstract

This systematic review explores the convergence of advanced quantitative methods, data engineering, and business intelligence in predictive workforce forecasting within contemporary human resource management. Guided by the PRISMA framework, 82 peer-reviewed studies published between 2010 and 2024 were analyzed to identify trends, tools, and challenges in the development and application of predictive HR analytics systems. The findings reveal a significant shift toward machine learning models—particularly random forests, logistic regression, and XGBoost—which consistently outperform traditional statistical methods in predicting workforce outcomes such as attrition, promotion, and role alignment. These models are heavily reliant on robust SQL-driven data pipelines that ensure scalable data extraction, transformation, and normalization from multiple HR systems. Additionally, Power BI dashboards emerged as a critical interface for operationalizing predictive insights, enabling real-time visualization of KPIs and model outputs for HR leaders and business stakeholders. Sector-specific evidence across healthcare, IT, manufacturing, and public services confirms the practical applicability and business value of these frameworks. Model validation practices—such as cross-validation, AUC, RMSE, and MAPE—are increasingly coupled with organizational KPIs including time-to-fill, cost-per-hire, and engagement lift. Ethical and governance considerations, including fairness-aware modeling, GDPR compliance, and algorithmic transparency, have also gained prominence, reflecting a growing emphasis on responsible AI in HR contexts. The review concludes that effective workforce forecasting requires not only technical sophistication but also ethical oversight, stakeholder alignment, and seamless integration across data infrastructure and decision systems. This synthesis contributes to the advancement of evidence-based, ethically grounded, and scalable HR forecasting frameworks that support strategic talent management in data-intensive organizational environments.