INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Employee Attrition System: Using Machine Learning to Evaluate Performance of the Staff
Authors Name:
Asiya Anjum
Unique Id:
IJSDR2211015
Published In:
Volume 7 Issue 11, November-2022
Abstract:
Employee’s attrition prediction has recently become a major issue in organizations. Employee turnover is a notable problem for organizations, particularly when highly qualified, technical, and key employees leave for better opportunities. This results in a loss of income because a trained employee must be replaced. As a result, we evaluate the common reasons for employee attrition using recent and historical employee data. Methods for supervising machine learning are described, demonstrated, and implemented. Evaluated for predicting employee turnover within an organization In this study, numerical experiments for real and simulated human resources datasets representing organizations with small, medium, and large employee populations are performed on the human resource data using Decision Tree, Logistic Regression, SVM, KNN, Random Forest, and Naive Bayes methods. To prevent employee attrition, we apply the feature selection method to the data and analyze the results. This helps companies predict employee attrition and helps their economic growth by lowering human resource costs.
Keywords:
— Employee, Opportunities, Predicting, Decision Tree, Logistic Regression, SVM, KNN, Random Forest, and Naive Bayes methods, Machine Learning, Cost, Data mining, Data base, Data Science.
Cite Article:
"Employee Attrition System: Using Machine Learning to Evaluate Performance of the Staff ", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.7, Issue 11, page no.83 - 95, November-2022, Available :http://www.ijsdr.org/papers/IJSDR2211015.pdf
Downloads:
000337209
Publication Details:
Published Paper ID: IJSDR2211015
Registration ID:202441
Published In: Volume 7 Issue 11, November-2022
DOI (Digital Object Identifier):
Page No: 83 - 95
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn