Quantitative Emotional Salary and Talent Commitment in Universities: An Unsupervised Machine Learning Approach

Abstract

In the world of academia, there is a great mobility of talented university professors with a high level of movement among different entities. This could be a major problem, as universities must retain a minimum level of talent to support their various academic programmes. In this sense, finding out what factors could increase the loyalty of such staff can be of great interest to human resource (HR) departments and the overall administrative management of an organisation. Thus, this area, also known as People Analytics (PA), has become very powerful in human resource management to strategically address challenges in talent management. This paper examines talent commitment within the university environment, focusing on identifying key factors that influence the loyalty of professors and researchers. To achieve this, machine learning (ML) techniques are employed, as Principal Component Analysis (PCA) for dimensionality reduction and clustering techniques for individual segmentation have been employed in such tasks. This methodological approach allowed us to identify such critical factors, which we have termed Quantitative Emotional Salary (QES), enabling us to identify those factors beyond those merely related to compensation. The findings offer a novel data-driven perspective to enhance talent management strategies in academia, promoting long-term engagement and loyalty.

Ähnliche Arbeiten