We investigate the role of the initial screening order (ISO) in candidate screening processes, such as employee hiring and academic admissions. The ISO refers to the order in which the screener evaluates the candidate pool. It has been largely overlooked in the literature, despite its potential impact on the optimality and fairness of the chosen set, especially under a human screener. We define two problem formulations: the best-$k$, where the screener selects the $k$ best candidates, and the good-$k$, where the screener selects the $k$ first good-enough candidates. To study the impact of the ISO, we introduce a human-like screener and compare it to its algorithmic counterpart. The human-like screener is conceived to be inconsistent over time due to fatigue. Our analysis shows that the ISO, in particular, under a human-like screener hinders individual fairness despite meeting group level fairness. This is due to the position bias, where a candidate's evaluation is affected by its position within the ISO. We report extensive simulated experiments exploring the parameters of the best-$k$ and good-$k$ problem formulations both for the algorithmic and human-like screeners. This work is motivated by a real world candidate screening problem studied in collaboration with a large European company.

翻译：我们研究了初始筛选顺序（ISO）在候选人筛选流程（如员工招聘和学术录取）中的作用。ISO 指筛查者评估候选人池的顺序。尽管ISO对所选集合的最优性与公平性（尤其在有人类筛查者参与时）具有潜在影响，但文献中对此关注甚少。我们定义了两种问题形式：最佳-k问题，即筛查者选择k名最佳候选人；以及良好-k问题，即筛查者选择前k名符合要求的候选人。为探究ISO的影响，我们引入了一种人类模拟筛查者，并将其与算法筛查者进行对比。该人类模拟筛查者被构想为因疲劳而随时间产生不一致性。分析表明，ISO（尤其在有人类筛查者的情况下）会阻碍个体公平性，尽管在群体层面仍能实现公平。这是由于位置偏差所致——候选人在ISO中的位置影响其评估结果。我们通过大量模拟实验，对算法与人类模拟筛查者在最佳-k和良好-k问题形式下的参数进行了探索。本研究源于与一家欧洲大型企业合作解决的实际候选人筛选问题。