Smart Investigation Through Machine Learning: Study On Faculty Selection In A Large Multi-Disciplinary University Of North-Eastern India
Main Article Content
Abstract
The selection of faculty members in a higher education institute like a university is a difficult task, as these selections impact the learning of the students who join the university with high hopes and aspirations; hence, the essential requirement for selection is to be fair and trustworthy. Using the Support Vector Regression (SVR) model, this paper explores the characteristics of university faculty members' smart rating through various metrics such as self-assessment through the Performance-Based-Appraisal System (PBAS) designed by UGC and Behavioural Competency Evaluation mechanism of the university authority. Through rigorous data pre-processing and feature selection, an SVR is a trained model to classify faculty based on predefined quality labels. Our work demonstrates the ability of SVR to neutrally observe and interpret factors affecting faculty performance in a university-based HR cell setting. The suggested techniques will be widely adopted, particularly for their significant implications in faculty recruitment processes within the HR domain.