Chapter 7: Machine learning in HR staffing
Restricted access

Effective human resources management (HRM) is a key component that firms need to establish in the modern economy. One task of HRM is staffing employees to open vacancies guided by organizational needs and requirements. However, human resources (HR) staffing comprises the net employee requirements necessary for day-to-day business and reserve requirements to cope with employee workplace absenteeism. Furthermore, staffing includes the available number of employees, subject to additional hires and employee attrition. Recent studies expounded the possible supportive role of modern technologies, such as Machine Learning (ML), for HR staffing tasks. In this chapter, we report a systematic literature review based on 65 pieces to elaborate the usage of ML in HR staffing. We focus on the prediction of net requirements and absenteeism, as well as hires and attrition. This investigation brought forth a dysbalance in the focus of conducted research, as most authors focus on predicting employee attrition, while only a few regard new hires. Additionally, no single best-suited ML method is prominent in HR staffing, as the predictions base on the availability of different data- and feature sizes. A majority of the reviewed papers solely use publicly available HR data for their predictions, limiting the real-world likelihood of actual work-related human behavior predictions.

You are not authenticated to view the full text of this chapter or article.

Access options

Get access to the full article by using one of the access options below.

Other access options

Redeem Token

Institutional Login

Log in with Open Athens, Shibboleth, or your institutional credentials

Login via Institutional Access

Personal login

Log in with your Elgar Online account

Login with your Elgar account
Edited by