Attrition Prediction and Retention of High Risk Employees Using Machine Learning and Explainable Artificial Intelligence
Author
Sidharth Nigade, Amit Shinde, Nikhil Dethe, Ganesh Chormale, Vaishali Kandekar
Abstract
The Indian Express’ reports that the
attrition rate in the IT industry has surpassed 25%. The majority of Fortune
500 firms are currently looking for new employees. On the one hand, there are
more opportunities, but according to a report by Employee Benefits News,
companies are also losing a significant amount of money - about 33% of their
annual income. The current era in which the IT industry serves as the
foundation for the economies of the world's leading nations. It's interesting
to note that 36% of these individuals don't even have their next job secured.
The cost of attrition includes both monetary and non-monetary costs, like
halted billing, delayed product launches, lack of reliability, etc. Our
objective is to determine the causes of attrition and implement preventative
actions as a result. The ideal answer was one-on-one interaction with HR, but
as we are well aware, it is not scalable. The only option left to us is to use
the Data to replicate this ideal state. Use the machine learning model to reliably
predict the attrition rate based on all of the available data. Consequently, in
this forthcoming modern period where the economics of the world's top-tier
countries are centered on the IT industry, recognizing attrition is crucial.
While discussing attrition, Bill Gates once said, "If the top 1% of
skilled employees leave Microsoft, the company declines from an extraordinary
to an average company. As a result, the goal of this paper is to provide
customized software to predict the employee retention rate based on supervised
and unsupervised machine learning algorithms by analyzing Glassdoor reviews as
well as churn dataset to reduce the cost of Employee turnover, to find the
potential factors responsible for voluntarily increase in attrition rate, to provide
better work life for the employees, etc. Lime which is a library of XAI is used
to predict the top 10 important features for the particular employees leaving
the organization. Algorithms like Backward selection, logistic regression,
decision trees and Random forest regressor were used. Along with this measures
were taken to fill the positions or retain the employees using XAI methods.
Keywords
Machine Learning, React, Node, Random forest, Logistic Regression, eXplainaible Artificial Intelligence
Full Text:
Download Paper PDF
References
- Towards Understanding Employee Attrition using a Decision Tree Approach Saadat M Alhashmi College of Computing and Informatics University of Sharjah Sharjah, UAE 19653360, 2020
- Abhiroop Nandi Ray; Judhajit Sanyal "Machine Learning Based Attrition Prediction" 2019 (GCAT) IEEE
- ] Vimoli Mehta, Shrey Modi, "Employee Attrition System Using Tree Based Ensemble Method", 2021 2nd International Conference on Communication, Computing and Industry 4.0 (C2I4), pp.1-4, 2021.
- A Review of Employee Motivation Theories and their Implications for Employee Retention within Organizations Sunil Ramlall, Ph.D., University of St. Thomas, Minneapolis, MN International Journal of Research Publication and Reviews, Vol 4, no 6, pp 1151-1154 June 2023 1154
- Nikita Tresa Cyriac, Kamaladevi Baskaran A Study on the Effectiveness of Non-Monetary Retention Strategies in UAE 2020 8th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)
- S. Shankar, J. Rajanikanth, V. V. Sivaramaraju and K. VSSR Murthy, "PREDICTION OF EMPLOYEE ATTRITION USING DATA MINING," 2018 IEEE International Conference on System, Computation, Automation and Networking (ICSCA), Pondicherry, 2018, pp. 1-8.
- Yadav, A. Jain and D. Singh, "Early Prediction of Employee Attrition using Data Mining Techniques," 2018 IEEE 8th International Advance Computing Conference (IACC), Greater Noida, India, 2018, pp. 349-354
- Wilson, “Predicting Employee Churn with Data Mining - CDO Advisors,”2017. Predicting-employee-churn-datamining [Accessed: 06-Jan-2019].
- Shobhit Aggarwal, Mugdha Sharma "Employee Attrition Prediction Using Machine Learning Comparative Study" IMAES pp 453–466 2021.
- H. Mobley, “Intermediate linkages in the relationship between job satisfaction and employee turnover.,” J. Appl. Psychol., vol. 62, no. 2, p. 237, 2016.
- Sarahi Aguilar-Gonzalez, Leon Palafox "Prediction of Student Attrition Using Machine Learning" MICAI 2019.
- Frye, C. Boomhower, M. Smith, L. Vitovsky, and S. Fabricant, “Employee Attrition: What Makes an Employee Quit?,” SMU Data Sci. Rev., vol. 1, no. 1, p. 9, 2018.
Share your valuable work from Social Media Buttons