Authors:
Manoj Parasa, Prameela Durga Bhavani Katari
Addresses:
Department of Information Technology Services, Ernst and Young, Dallas, Texas, United States of America. Department of Information Technology Services, Accenture, Hyderabad, Telangana, India.
Abstract:
Organisations are placing more emphasis on the need to obtain rapid insights about the performance of their workforce as well as the dynamics of their talent pool. This study introduces a real-time, hosted framework for workforce analytics in SAP SuccessFactors, powered by the SAP Business Technology Platform (BTP) and with embedded machine learning (ML) capabilities. Within a company's workflows, the framework integrates a variety of human resource (HR) data sources to provide predictive, actionable insights. The research uses the SAP Integration Suite, AI Core, and SAP Analytics Cloud (SAC) to demonstrate how anomaly detection, predictive modelling, and sentiment analysis can be applied in human resources systems. To verify the correctness, managerial impact, and system latency, a mixed-methods approach was employed. This technique included HR decision-support assessments, data engineering pipelines, and supervised machine learning algorithms. A considerable improvement in the accuracy of human resources forecasting was discovered, along with a 37% reduction in analytical response time (AUC = 0.91, precision = 0.86, recall = 0.85). In addition to technological advancements, this research establishes an evidence-based paradigm for intelligent, ethical, and transparent human resource decisions. This model also contributes to improving organisational agility and workforce sustainability.
Keywords: SAP SuccessFactors; Machine Learning; Predictive Analytics; Workforce Forecasting; Human Capital Management; Real-Time Dashboards; Artificial Intelligence (AI); Digital Transformation.
Received: 22/10/2024, Revised: 25/12/2024, Accepted: 24/02/2025, Published: 09/09/2025
DOI: 10.64091/ATITP.2025.000156
AVE Trends in Intelligent Technoprise Letters, 2025 Vol. 2 No. 3 , Pages: 118-126