“Leveraging Machine Learning for Predictive HR Analytics: A Study on Employee Attrition in the Digital Era”
Gayatri S. Kukade1,
Student
Dept. of MBA., Sipna College of Engineering and Technology, Amravati 444607, Amravati (MS.), India
gayatrikukade2004@gmail.com
Prof. Kasturi Kashikar 2
Asst. Professor,
Dept. of MBA., Sipna College of Engineering and Technology, Amravati 444607, Amravati (MS.), India
kdkashikar@sipnaengg.ac.in
Abstract
Employee attrition has become a critical challenge for organizations in the digital era, where retaining skilled talent is essential for sustaining a competitive advantage. This study explores the use of machine learning and predictive HR analytics to analyze and manage employee attrition effectively. The research examines trends in attrition over multiple years, identifies high-risk departments, and analyzes tenure-based turnover patterns. Visualizations including line charts, bar charts, and pie charts are employed to present findings in a clear and meaningful manner.
The study reveals a gradual increase in overall attrition, with departments such as Nursing and Operations experiencing disproportionately higher turnover. Employees with less than two years of tenure contribute the majority of attrition, emphasizing the need for structured onboarding, mentorship programs, and early career development initiatives. These findings highlight the strategic value of predictive HR analytics in forecasting attrition risks and supporting timely interventions.
By integrating historical trend analysis with predictive modeling, this research provides actionable insights for HR professionals, enabling data-driven decision-making and improving workforce planning. The study contributes to the growing field of HR analytics, demonstrating how machine learning can transform traditional HR practices into proactive, evidence-based strategies that enhance employee engagement and retention.
Keywords: Employee Attrition, Predictive HR Analytics, Machine Learning, Workforce Retention, Digital Era
