An Infographic Approach for Employee Attrition for Corporate Company Based on Hard and Soft Voting Classifiers.

Abstract

Attrition, also referred to as employee turnover or staff churn, is a significant problem for businesses operating in a variety of different industries. If organizations can anticipate and comprehend the variables that contribute to attrition, they will be in a better position to be able to take preventative action and reduce the negative repercussions of this phenomenon. In recent years, machine learning algorithms have matured into sophisticated tools that can analyze vast quantities of data and identify tendencies that could lead to attrition. One of the most important applications of these techniques is in the healthcare industry. For this research, a dataset was obtained from a corporate company in Nashik City. Additionally, to evaluate machine learning algorithms, Logistic Regression, Decision Trees, KNN, Support Vector Classifiers (SVC), and Ensemble Learning Hard and Soft Voting Classifiers were proposed. The ensemble soft model and the DT soft model have the best accuracy, precision, recall, and F1-score values at 0.909, whereas the SVC and LR soft models have a sensitivity of 0.1 and 1.0, respectively. The F1 score obtained by the SVC also has the worst accuracy, precision, and recall (0.680), as well as the lowest score overall.