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.

中文翻译：

---

利用分组数据构建预测模型：离职意向预测案例研究

大数据的可用性刺激了现代预测分析（例如机器学习方法）在人力资源管理（HRM）研究和实践中的应用。由于预测分析的新颖性和技术性，人力资源专业人员和研究人员可能很难与数据专家合作。我们全面介绍了预测方法的逻辑和价值。此外，我们强调了处理分组数据的问题——这在人力资源管理研究中很常见，但在构建预测模型中却很少讨论。我们在应用预测模型时引入了不同的策略来处理分组数据。在由 199 家中小企业的 1454 名员工组成的经验数据集中比较了不同建模方法和预测模型的性能。按照比较预测模型相对性能的工作流程，具有最佳预测精度的模型是随机效应袋装树，它允许复杂的关系并包含随机效应。根据该模型的估计，我们确定了离职意向的五个最有影响力的预测因素：感知公平性、领导者与成员之间的交流、职业机会、薪酬满意度和年龄。预测模型的归纳性质预计将促进理论发展和人力资源分析，以制定有效的人力资源管理政策。