Abstract
Employees are the most valuable resources for any organization. The cost associated with professional training, the developed loyalty over the years and the sensitivity of some organizational positions, all make it very essential to identify who might leave the organization. Many reasons can lead to employee attrition. In this paper, several machine learning models are developed to automatically and accurately predict employee attrition. IBM attrition dataset is used in this work to train and evaluate machine learning models; namely Decision Tree, Random Forest Regressor, Logistic Regressor, Adaboost Model, and Gradient Boosting Classifier models. The ultimate goal is to accurately detect attrition to help any company to improve different retention strategies on crucial employees and boost those employee satisfactions.
Highlights
More than half of organizations have several challenges in retaining the most marketable or high-performance employees [1]
It is worth notice that the best performance ensemble were the ensemble consists of the Decision trees (DT) and the Logistic regression (LR), the least complex models evaluated in this work
The performance of the ensembles is slightly lower than their best base models, these ensembles would generalize better for unseen examples and larger datasets
Summary
More than half of organizations have several challenges in retaining the most marketable or high-performance employees [1]. The assessment of retention risk and the estimating likelihood of leaving would support to establish or update retention strategies and to avoid the high cost associated with hiring and training new employees. To assess the employee attrition automatically, in this work we use IBM HR Analytics Employee Attrition Performance dataset available at Kaggle.org. This dataset has been analyzed by many analysts and they published their results on Kaggle’s kernel. Several machine learning models were trained, optimized and evaluated to predict weather a certain employee will leave the company or not and according to this predication the company will improve different retention strategies on targeted employee
Sign-in/Register to view highlights & summary 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: International Journal of Machine Learning and Computing
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.
