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

Abstract

AbstractThe 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.