Key points are not available for this paper at this time.
Human capital is a paramount asset within any organization, evolving into distinct facets that fortify its competitive edge amid a perpetually shifting market landscape. Securing high-quality candidates necessitates minimizing human intervention and validating candidate credentials during recruitment. Moreover, gauging employee performance and anticipating attrition prove pivotal in effective human resource management. This study endeavors to introduce an innovative human resource management system employing machine learning and blockchain. The objective is to create an intelligent system that reduces human subjectivity and time in candidate selection while forecasting employee performance and attrition. Leveraging unsupervised learning algorithms and natural language processing, the system conducts skill assessment and resumes categorization after the extraction of raw data via object character recognition. Candidate validation relies on comparing blockchain-stored records. Supervised machine learning classification predicts employee performance and attrition with high precision, generating standardized scores based on multiple attributes aligned with specific e-competence frameworks, aiming to foster workplace productivity while minimizing financial losses.
Chanda et al. (Sun,) studied this question.