Predicting employee retention using artificial intelligence and survival analysis approaches | ||
| Journal of Artificial Intelligence in Engineering Practice | ||
| Volume 2, Issue 1, April 2025, Pages 31-38 PDF (628.09 K) | ||
| Document Type: Original Article | ||
| DOI: 10.21608/jaiep.2025.431657.1030 | ||
| Authors | ||
| Serifat A Folorunso* 1; Richard O Kehinde2; Morufu A Folorunso3 | ||
| 1University of Ibadan, Laboratory for Statistical Analysis (UI-LISA), Department of Statistics, Nigeria | ||
| 2Federal College of Animal Health and Production Technology, Department of Statistics, Moor Plantation, Ibadan, Oyo State, Nigeria | ||
| 3Federal School of Statistics, General Studies Department, Sasa Road, Ibadan, Nigeria | ||
| Abstract | ||
| Background: Employee retention is a critical concern for organizations seeking to maintain a stable and productive workforce. Understanding the factors driving turnover is essential for designing effective HR interventions. Methods: This study applies advanced survival analysis techniques, including the Kaplan–Meier estimator, Cox proportional hazards model, and Random Survival Forests (RSF), to predict employee retention and identify key determinants of turnover. Data from 1,480 employees, with 16% (238) having left the organization, were analyzed, considering variables such as age, job satisfaction, overtime, and departmental affiliation. Results: Employees working overtime are 3.57 times more likely to leave, indicating overtime as a major risk factor. In contrast, older employees and those with higher job satisfaction show reduced turnover risks, with hazard ratios of 0.93 and 0.79, respectively. Departmental differences were observed, with Research & Development exhibiting the highest retention, including employees staying beyond 30 years, while Human Resources had the highest turnover, particularly within the first five years. Conclusion: The study highlights the importance of job satisfaction, overtime policies, and department-specific retention strategies in reducing turnover. Survival modeling provides actionable insights into the timing and drivers of employee exits, enabling organizations to implement targeted interventions that enhance workforce stability and long-term organizational success. | ||
| Keywords | ||
| Kaplan–Meier, Predictive Analytics, hazards model; Random survival forest; Workforce sustainability | ||
|
Statistics Article View: 19 PDF Download: 10 |
||
