[论文解读] "How to make them stay?" -- Diverse Counterfactual Explanations of Employee Attrition

André Artelt, Andreas Gregoriades|arXiv (Cornell University)|Mar 8, 2023

AI and HR TechnologiesBusiness, Management and Accounting被引用 3

一句话总结

本文提出了一种新颖的框架，通过分析多个历史案例中的集体特征变化，生成多样化的、政策层面的反事实解释，以减少员工流失。通过优化如加薪和减少上次晋升以来的时间等干预措施，该方法提供了优于个体案例解释且与保留文献一致的可操作HR策略。

ABSTRACT

Employee attrition is an important and complex problem that can directly affect an organisation's competitiveness and performance. Explaining the reasons why employees leave an organisation is a key human resource management challenge due to the high costs and time required to attract and keep talented employees. Businesses therefore aim to increase employee retention rates to minimise their costs and maximise their performance. Machine learning (ML) has been applied in various aspects of human resource management including attrition prediction to provide businesses with insights on proactive measures on how to prevent talented employees from quitting. Among these ML methods, the best performance has been reported by ensemble or deep neural networks, which by nature constitute black box techniques and thus cannot be easily interpreted. To enable the understanding of these models' reasoning several explainability frameworks have been proposed. Counterfactual explanation methods have attracted considerable attention in recent years since they can be used to explain and recommend actions to be performed to obtain the desired outcome. However current counterfactual explanations methods focus on optimising the changes to be made on individual cases to achieve the desired outcome. In the attrition problem it is important to be able to foresee what would be the effect of an organisation's action to a group of employees where the goal is to prevent them from leaving the company. Therefore, in this paper we propose the use of counterfactual explanations focusing on multiple attrition cases from historical data, to identify the optimum interventions that an organisation needs to make to its practices/policies to prevent or minimise attrition probability for these cases.

研究动机与目标

• 通过数据驱动的、可操作的HR政策而非个体案例解释，解决预防员工流失的挑战。
• 克服传统可解释性方法（如SHAP）的局限，生成与政策相关的建议。
• 在多个流失案例中识别出最优且一致的特征值变化，以最小化流失概率。
• 为HR部门提供可扩展、可泛化的建议，以改善关键员工群体的留存率。
• 通过聚焦于集体性、可实施的改变，弥合黑箱机器学习模型与实际HR决策之间的差距。

提出的方法

• 同时对多个员工流失案例应用反事实解释技术，而非单个实例。
• 在数据标准化和随机欠采样处理后，对IBM员工流失数据集训练二元分类器（如XGBoost、随机森林），以解决类别不平衡问题。
• 通过识别对特征（如加薪、上次晋升以来的时间、工作满意度）的最小且一致的变化来生成反事实，从而逆转模型的流失预测。
• 通过优化生成多样化的反事实解决方案，以反映不同的政策选项（如加薪与提升工作满意度）。
• 通过超参数调优和交叉验证，确保模型在数据集上的鲁棒性和泛化能力。
• 通过与组织约束和留存驱动因素文献保持一致，优先考虑可行且现实的干预措施。

实验结果

研究问题

• RQ1 如何将反事实解释方法调整为在多个案例中生成减少员工流失的政策层面建议？
• RQ2 哪些特征变化组合（如薪资、工作满意度、晋升时机）最有效地逆转员工群体的流失预测？
• RQ3 在可行性与HR最佳实践的一致性方面，多样化反事实解决方案如何比较？
• RQ4 多实例反事实是否能优于个体案例解释，提供更具可操作性的HR策略？
• RQ5 组织可以实施哪些最具影响力且低成本的干预措施，以大规模降低员工流失？

主要发现

• 预测显示，薪资涨幅提高40%可将多个员工案例的流失概率降至较低水平。
• 将上次晋升以来的时间减少约5年，可显著降低流失的可能性。
• 结合20%的薪资涨幅与50%的工作满意度提升，能有效逆转流失预测。
• 该方法识别出薪资、工作满意度和晋升时机是防止流失的最关键因素，与现有留存文献一致。
• 针对多个案例生成的反事实提供了比个体案例解释更具可扩展性和可操作性的HR政策建议。
• 该方法生成了多样化且可行的干预策略，未来可按实施难度进行排序。