Predicting Absenteeism and Temporary Disability Using Machine Learning: a Systematic Review and Analysis
- PDF / 919,837 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 96 Downloads / 202 Views
SYSTEMS-LEVEL QUALITY IMPROVEMENT
Predicting Absenteeism and Temporary Disability Using Machine Learning: a Systematic Review and Analysis Isabel Herrera Montano 1 la Torre Díez 1
& Gonçalo Marques
2
& Susel Góngora Alonso
1
& Miguel López-Coronado
1
& Isabel de
Received: 22 March 2020 / Accepted: 21 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The main objective of this paper is to present a systematic analysis and review of the state of the art regarding the prediction of absenteeism and temporary incapacity using machine learning techniques. Moreover, the main contribution of this research is to reveal the most successful prediction models available in the literature. A systematic review of research papers published from 2010 to the present, related to the prediction of temporary disability and absenteeism in available in different research databases, is presented in this paper. The review focuses primarily on scientific databases such as Google Scholar, Science Direct, IEEE Xplore, Web of Science, and ResearchGate. A total of 58 articles were obtained from which, after removing duplicates and applying the search criteria, 18 have been included in the review. In total, 44% of the articles were published in 2019, representing a significant growth in scientific work regarding these indicators. This study also evidenced the interest of several countries. In addition, 56% of the articles were found to base their study on regression methods, 33% in classification, and 11% in grouping. After this systematic review, the efficiency and usefulness of artificial neural networks in predicting absenteeism and temporary incapacity are demonstrated. The studies regarding absenteeism and temporary disability at work are mainly conducted in Brazil and India, which are responsible for 44% of the analyzed papers followed by Saudi Arabia, and Australia which represented 22%. ANNs are the most used method in both classification and regression models representing 83% and 80% of the analyzed works, respectively. Only 10% of the literature use SVM, which is the less used method in regression models. Moreover, Naïve Bayes is the less used method in classification models representing 17%. Keywords Absenteeism . Temporary disability . Machine learning . Artificial neural networks
This article is part of the Topical Collection on Systems-Level Quality Improvement
Introduction
* Isabel de la Torre Díez [email protected]
Artificial neural networks (ANNs) models consist of simple processing units, called artificial neurons. These models are inspired by the structure of the brain and aim to simulate human behaviour, such as learning, association, generalization, and abstraction, when undergoing training [1, 2]. ANNs can solve nonlinear and poorly defined problems based on a parallel composition through experience, being able to work with incomplete, inaccurate, or high-noise data [3, 4]. Neural networks allow useful information to be extracted and inferences from the data available conc
Data Loading...
