International Journal of Science, Engineering and TechnologyAuthors: Nisha Kulkarni, Rohan Mehta, Arvind Sethi, Vasudev Sharma
Abstract: Organizations operating in dynamic labor markets increasingly depend on advanced workforce intelligence capabilities to understand how roles evolve, how skills diffuse, and how employees move across functions within complex enterprise environments. Traditional analytics in SAP SuccessFactors landscapes often rely on static hierarchical models and structured records that provide limited visibility into the multidimensional patterns shaping workforce behavior. This study proposes a generative AI guided workforce intelligence graph framework that captures employees, roles, skills, credentials, learning histories, and mobility events as interconnected structures capable of representing both explicit and inferred relationships. The framework integrates graph modeling, semantic enrichment, and generative AI reasoning to produce context aware insights for role transition forecasting, emerging skill identification, and internal mobility prediction. A mixed methodological approach combining architectural modeling, graph construction, temporal pattern analysis, and generative AI based inference was employed to evaluate how enriched graph representations improve predictive reliability across diverse workforce scenarios. Findings demonstrate that graph enhanced and AI guided embeddings significantly strengthen the accuracy and interpretability of mobility forecasting, reduce the effort required to identify skill adjacency patterns, and provide managers with narrative insights that align with real world workforce dynamics. The study contributes an extensible design blueprint for enterprises seeking to modernize workforce planning, enhance decision support, and operationalize future ready HR ecosystems within SAP SuccessFactors landscapes.
DOI: http://doi.org/10.5281/zenodo.17895770
