Applied Machine Learning Techniques on Selection and Positioning of Human Resources in the Public Sector

Abstract

Proper selection and positioning of employees is an important issue for strategic human resources management. Within this framework, the aim of the research conducted, was to investigate the most efficient machine learning techniques to support employees’ recruitment and positioning evaluation. Towards this aim, a series of tests were conducted based on classification algorithms concerning employees of the public sector, seeking to predict best fit in workplaces and allocation of employees. Based on the outcome of the administered tests, an algorithm model was built to assist the decision support system of employees’ recruitment and assessment. The primary findings of the present research could lead to the argument that the adoption of the Employees’ Evaluation for Recruitment and Promotion Algorithm Model (EERPAM) will significantly improve the objectivity of employees’ recruitment and positioning procedures.