Bias-aware AI for Human Capital Management: An Innovative Approach for Algorithmic Job Screening

Alex Miller and Kartik Hosanagar, Operations, Information, and Decisions, The Wharton School

Abstract: A well-known maxim in management is that “your people are your greatest asset”. Recruitment strategies in particular have been linked to firms’ innovative capacity, emphasizing the importance of maintaining competitive advantages in HR as a key goal of effective innovation management. Despite the consensus on the value of effective recruitment, most firms continue to practice inefficient, poorly managed strategies. An emerging possibility to address these organizational deficiencies is the application of novel techniques from artificial intelligence. However, many commentators are rightly concerned about the potential for algorithms trained on historical data to perpetuate discriminatory biases in pernicious, opaque ways. In this research project, we propose using statistical theory to augment historically “bias-naive” algorithms with “bias-aware” algorithms that are designed to counteract the effects of historical bias. We have already developed a mathematical model that indicates our job screening method can reduce algorithmic bias while maintaining high levels of accuracy. Our primary objective is to demonstrate empirically that our technique can achieve these goals in real-world environments. If our method proves successful, it has the potential to dramatically improve the efficiency and accuracy of existing recruiting practices, while avoiding the discriminatory impact of existing bias-naive techniques.