Abstract
The objective of this paper is to study the problem of employee turnover prediction and to develop a classifier that uses employee's data to identify those who have a greater tendency to leave the company voluntarily. For such purpose, the data of 8724 employees from a real Brazilian beverage company was used to train an Extreme Learning Machine (ELM) classifier, assigning to each sample a weight inversely proportional to the size of the respective class. After the training, the classifier displayed an overall accuracy of 79% of the test data.
Highlights
Employee turnover can cause instability and unexpected expenses for the organization
The objective of this paper is to study the problem of employee turnover prediction and to develop a classifier that uses employee's data to identify those who have a greater tendency to leave the company voluntarily
The data of 8724 employees of a real Brazilian beverage company were used. 15% of them voluntarily resigned, 11% were dismissed from their jobs, and 74% remain active in the company
Summary
Employee turnover can cause instability and unexpected expenses for the organization. The motivations leading an employee to leave a company are often complex and difficult to identify, so machine learning models have been used successfully to address problems similar to the Turnover problem. The model goes through a training step that is performed automatically from existing data, after the training stage the model is able to make predictions from new data. The present work studied several machine learning models and applied the knowledge studied using Extreme Learning Machines (ELM), a type of artificial neural network with a single hidden layer whose weights are fixed randomly and the weights of the output layer can be trained through the least squares method, which grants ELMs a simple and fast training, alongside a good generalization performance [1].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Revista dos Trabalhos de Iniciação Científica da UNICAMP
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
