International Journal of Science, Engineering and TechnologyAuthors: Manoj Parasa F
Abstract: This study investigates the increasing demand for intelligent recruitment capabilities within enterprise talent acquisition systems, focusing on the limitations of manual screening practices and static filtering methods that struggle to handle rising applicant volumes and evolving role complexity. Traditional selection workflows often lack precision, depend on subjective interpretation, and provide limited support for identifying candidate potential beyond surface level profile attributes. To address these constraints, the research introduces a modern recruitment intelligence framework that integrates predictive scoring techniques with adaptive talent pooling mechanisms within the SAP SuccessFactors Recruiting environment. A mixed methods design is employed, combining quantitative evaluation of machine learning based scoring models with qualitative examination of recruiter behavior, process interactions, and system level data characteristics. The findings demonstrate that predictive scoring significantly improves shortlist accuracy, reduces manual review effort, and strengthens alignment between job requirements and candidate competencies. Adaptive talent pooling further enhances the breadth and relevance of available candidate segments by dynamically grouping profiles based on contextual fit signals rather than fixed keyword rules. The proposed framework offers a structured and practical approach for embedding predictive analytics into enterprise recruitment platforms, contributing both methodological clarity and operational value. Overall, the study advances the understanding of how data driven assessment and intelligent talent segmentation can elevate recruitment efficiency, improve decision support, and support more strategic workforce planning.
DOI: http://doi.org/10.5281/zenodo.17695684
