Building prediction models with grouped data: A case study on the prediction of turnover intention

2021/07/16 by Shuai Yuan, Brigitte Kroon, Astrid Kramer
Business, Management and Accounting · Social Sciences · #AI and HR Technologies #Customer churn and segmentation #Retirement, Disability, and Employment

paper · pdf · doi:10.1111/1748-8583.12396

openalex publication_date 2021/07/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01

Abstract

Abstract The availability of big data spurred the application of modern prediction analytics (e.g., machine learning methods) in human resource management (HRM) research and practice. Due to the novel and technical nature of prediction analytics, HR professionals and researchers may struggle to collaborate with data experts. We offer a comprehensive introduction to the logic and value of prediction methods. Moreover, we highlight the concern of treating grouped data—commonly seen in HRM research yet rarely discussed in building prediction models. We introduce different strategies to deal with grouped data in applying prediction models. The performance of different modelling approaches and prediction models are compared in an empirical data set consisting of 1454 employees from 199 small and medium sized enterprise's. Following a workflow to compare the relative performance of the prediction models, the model with the best prediction accuracy was the random‐effects bagged tree that allows for complex relationships and incorporates random effects. Following the estimates of this model, we identified the five most influential predictors of turnover intention: perceived fairness, leader‐member exchange, career opportunities, pay satisfaction and age. The inductive nature of prediction models is expected to advance theory development and HR analytics for developing effective HRM policies.

Citations

• Random-Effects Models for Longitudinal Data
• Sources of Method Bias in Social Science Research and Recommendations on How to Control It
• On the unnecessary ubiquity of hierarchical linear modeling.
• An evidence-based review of HR Analytics
• One hundred years of employee turnover theory and research.
• Fixed and random effects models: making an informed choice
• A quarter‐century review of HRM in small and medium‐sized enterprises: Capturing what we know, exploring where we need to go
• The generalizability crisis

Related

• Can Large Language Model Predict Employee Attrition?
• Employee Turnover Prediction: A Cross-component Attention Transformer with Consideration of Competitor Influence and Contagious Effect
• Employee turnover prediction and retention policies design: a case study
• Employee Turnover Analysis Using Machine Learning Algorithms
• New methods for new data? An overview and illustration of quantitative inductive methods for HRM research