Prediction of Employee Turnover in Organizations using Machine Learning Algorithms

Abstract

Abstract-Employee turnover has been identified as a key issue for organizations because of its adverse impact on work place productivity and long term growth strategies. To solve this problem, organizations use machine learning techniques to predict employee turnover. Accurate predictions enable organizations to take action for retention or succession planning of employees. However, the data for this modeling problem comes from HR Information Systems (HRIS); these are typically under-funded compared to the Information Systems of other domains in the organization which are directly related to its priorities. This leads to the prevalence of noise in the data that renders predictive models prone to over-fitting and hence inaccurate. This is the key challenge that is the focus of this paper, and one that has not been addressed historically. The novel contribution of this paper is to explore the application of Extreme Gradient Boosting (XGBoost) technique which is more robust because of its regularization formulation. Data from the HRIS of a global retailer is used to compare XGBoost against six historically used supervised classifiers and demonstrate its significantly higher accuracy for predicting employee turnover.

An Enhanced Deep Neural Network for Predicting Workplace Absenteeism

“…In this research study, a private company's data are used as a case study to test classification algorithms. Similarly, in [18][19][20], machine learning models are used to predict employee turnover. Also, in another study, data mining techniques are used to predict employee turnover [21].…”

Avant-propos

“…D'autres travaux de recherche similaires laissent penser que les variables personnelles ou démographiques -à savoir l'âge, le sexe, l'appartenance ethnique, la formation et la situation matrimoniale -constituent d'importants facteurs prédictifs de la rotation volontaire. D'autres caractéristiques ont également été étudiées : le salaire, les conditions de travail, la satisfaction professionnelle, l'encadrement, la progression de carrière, la reconnaissance, les possibilités d'évolution professionnelle et le burn-out (Punnoose et Pankaj, 2016).…”

Sentiment analysis in organizational work: Towards an ontology of people analytics

“…In the past few years, various studies have explored the use of artificial intelligence, data mining, machine learning, and Internet of Things for various HR purposes, such as candidate selection, employee mood and sentiment analysis, and churn prediction. Different methods have been used to this end: correlating job requirements with individual résumés (Bollinger, Hardtke, & Martin, ; Yi, Allan, & Croft, ); analysing candidate video clips (such as provided by HireVue) and identifying characteristics or qualities incompatible with the job; predicting eventual and actual employee attritions by using prediction algorithms and social media data (Punnoose & Ajit, ; Robinson, Sinar, & Winter, ); identifying employee moods and emotions such as happiness, surprise, anger, disgust, fear, and sadness, by analysing facial expressions captured by the organization's cameras (facial emotion detection; Subhashini & Niveditha, ); analysing voice tones being used (Chan & Eric, ); analysing sentiments through online employee reviews (Moniz & Jong, ) and social media platforms (Costa & Veloso, ); and inspecting employee productivity by sensors installed on employee badges (Ara et al, ). Such sensors enable identifying movement, tone of voice, speech speed, employee cohesion, and so forth; exploring the effect of social media use on employee performance and motivation (Leftheriotis & Giannakos, ); and measuring employee knowledge sharing by analysing information shared in social media (van Zoonen, Verhoeven, & Vliegenthart, ) or in organizational intranets (Koriat & Gelbard, ; Koriat & Gelbard, ).…”