This paper analyzes the prediction performance of human resources (HR) variables in corporate failure modeling. We define corporate failure as a two-phase process from financial distress to bankruptcy, so that we can determine the prediction power of HR variables along a firm's phase in the financial deterioration process. We demonstrate the use of HR variables and their application to a two-phase corporate failure model, providing first evidence for the predictive power of HR variables. The experimental results, based on real-world datasets from Belgium, show that HR variables used in conjugation with accounting-based information improve the accuracy of prediction modeling. However, the predictive power of HR variables varies in different phases of corporate failure with better prediction accuracy during the initial symptoms of corporate failure (i.e., financial distress). Findings show that our proposed model predicted financial distress with 84.1%, whereas the accuracy decreased to 83.3% when predicting bankruptcy. Besides, they also show that, on average, the inclusion of HR variables improves the global accuracy of the prediction models of 3.8% and allows to decrease Type I error of 5%.

中文翻译：

---

人力资源和企业失败预测模型：来自比利时的证据

本文分析了人力资源 (HR) 变量在企业失败建模中的预测性能。我们将公司倒闭定义为从财务困境到破产的两阶段过程，以便我们可以确定人力资源变量在财务恶化过程中公司所处阶段的预测能力。我们展示了 HR 变量的使用及其在两阶段企业失败模型中的应用，为 HR 变量的预测能力提供了第一个证据。基于来自比利时的真实世界数据集的实验结果表明，与基于会计的信息结合使用的 HR 变量提高了预测建模的准确性。然而，人力资源变量的预测能力在企业失败的不同阶段有所不同，在企业失败的初始症状（即财务困境）期间具有更好的预测准确性。结果表明，我们提出的模型预测财务困境的准确率为 84.1%，而预测破产的准确率下降到 83.3%。此外，他们还表明，平均而言，包含 HR 变量可将预测模型的全局准确度提高 3.8%，并使 I 类错误降低 5%。