Int J Performability Eng ›› 2023, Vol. 19 ›› Issue (3): 203-215.doi: 10.23940/ijpe.23.03.p6.203215

Previous Articles     Next Articles

AI-Powered Workforce Analytics: Maximizing Business and Employee Success through Predictive Attrition Modelling

Shobhanam Krishnaa,* and Sumati Sidharthb   

  1. aIndian Institute of Management, Shillong, 793018, India;
    bDefence Institute of Advanced Technology, Pune, 411025, India
  • Contact: * E-mail address: shobhanam14@gmail.com

Abstract: The purpose of the paper is to introduce a machine learning model that utilizes the Logistics Regression algorithm to analyze the likelihood of employees leaving an organization. The paper seeks to identify key motivators that contribute to employee turnover and provide insights into how to reduce employee attrition rates. To accomplish this, the research delves into the factors that impact employee contentment and involvement, such as job security, opportunities for career advancement, maintaining a healthy work-life balance, and remuneration. Moreover, the effectiveness of the Logistics Regression algorithm in predicting employee turnover is being evaluated. The methodology used in the study involves the application of the Logistics Regression algorithm to evaluate important parameters related to employee retention. The model achieves an accuracy rate of 84.12 percent, a precision of 84 percent, and a recall rate of 100 percent. The study's findings can assist management in making informed decisions and implementing changes to retain employees, ultimately enhancing productivity and loyalty and increasing the organization's competitiveness. Focusing too much on predicting employee attrition may take attention away from other important aspects of managing employees, and different organizations may require different approaches to employee retention. However, using prediction models to identify potential flight risks and develop retention strategies can lead to a stable and productive workforce, positively impacting overall organizational performance. The paper's originality lies in its use of machine learning and predictive analytics to address a critical issue affecting organizational competitiveness.

Key words: artificial intelligence (AI), employee attrition, employee turnover, staff turnover, feature engineering, logistics regression (LR), machine learning (ML), accuracy, precision, recall, f1-score, confusion matrix