Reducing subgroup differences in personnel selection through the application of machine learning
Reducing subgroup differences in personnel selection through the application of machine learning
复制标题
通过机器学习的应用减少人员选拔中的亚组差异
DOI：
10.1111/peps.12593
复制
发表时间：
2023
影响因子：
5.5
通讯作者：
Song, Q. Chelsea
中科院分区：
文献类型：
--
作者：
Zhang, Nan;Wang, Mo;Xu, Heng;Koenig, Nick;Hickman, Louis;Kuruzovich, Jason;Ng, Vincent;Arhin, Kofi;Wilson, Danielle;Song, Q. Chelsea
研究人员已经调查了机器学习（ML）是否能够解决人员选拔中最根本的问题之一，即通过帮助减少种族和性别在选拔程序得分中的亚组差异（以及由此产生的不利影响）。本文介绍了三个这样的调查。研究结果表明，对（非线性）ML算法进行统计调整以减少子群差异的做法越来越多，这必然会产生预测偏差（差分预测）作为数学确定性。这可能会降低有效性，并无意中惩罚高分的少数民族。类似地，一种调整ML输入数据的方法仅略微降低了子组差异，但代价是略微降低了模型准确性。其他新兴的策略涉及加权预测，以平衡或找到减少亚组差异，同时保持有效性的竞争目标之间的妥协，但他们已被限制在两个结果。第三项调查将其扩展到三个结果（例如，有效性，亚组差异和成本），并提出了一个在线工具。总的来说，本文中的研究表明，ML不太可能解决不利影响的问题，但它可能有助于找到增量改进。
Researchers have investigated whether machine learning (ML) may be able to resolve one of the most fundamental concerns in personnel selection, which is by helping reduce the subgroup differences (and resulting adverse impact) by race and gender in selection procedure scores. This article presents three such investigations. The findings show that the growing practice of making statistical adjustments to (nonlinear) ML algorithms to reduce subgroup differences must create predictive bias (differential prediction) as a mathematical certainty. This may reduce validity and inadvertently penalize high‐scoring racial minorities. Similarly, one approach that adjusts the ML input data only slightly reduces the subgroup differences but at the cost of slightly reduced model accuracy. Other emerging tactics involve weighting predictors to balance or find a compromise between the competing goals of reducing subgroup differences while maintaining validity, but they have been limited to two outcomes. The third investigation extends this to three outcomes (e.g., validity, subgroup differences, and cost) and presents an online tool. Collectively, the studies in this article illustrate that ML is unlikely to be able to resolve the issue of adverse impact, but it may assist in finding incremental improvements.