Machine Learning driven Skill Prioritisation for Human Resource Planning

Performance Management1 is of paramount importance in Human Resources Planning. To address today's growing skill challenge, employers need to determine existing employee expertise deficit to achieve much needed business outcomes. Determining skill gap amongst employees helps the resource planners to decide between revising their hiring procedures to not overlook expert talent and expansion of their training programs for existing employees with the required skills to enhance their capacity to deliver future projects. This paper explores a well-known unsupervised learning algorithm: Collaborative filtering to predict and prioritise the employees across their domain expertise based on multiple factors such as existing domain expertise, location of the employees, availability of the employees, relevant learnings, prior experience and work performance to handle the skill specific projects in the future. Employee prioritisation for the future across domain specific expertise using this unsupervised machine learning algorithm will potentially help in optimizing the skilled resource pool and make the resource planning a bit seamless for operational resource managers in any industry vertical.