The CEPR International Virtual Organization Economics Seminars (CIVOE-Seminars) is a new seminar is aimed at drawing together organizational economics and personnel economics speakers during this time when our university and NBER conferences are occurring less frequently. We are also taking the opportunity to make this a truly international collection of colleagues and speakers. We will meet via a webinar bi-weekly on Mondays at 6 pm CEST.
Our first seminar will be on Monday 20th April 2020 at 6pm CEST / 5pm London / 12pm East Coast / 11am Chicago / 9am West Coast. Our speaker will be Danielle Li, MIT presenting on "Hiring as Exploration" with Peter Bergman and Lindsey Raymond.The abstract can be found below.
Title: Hiring as Exploration
Authors: Peter Bergman, Danielle Li and Lindsey Raymond.
Abstract: In looking for the best workers over time, firms must balance exploitation (selecting from groups with proven track records) with exploration (selecting from under-represented groups to learn about quality). Yet modern hiring algorithms, based on "supervised learning" approaches, are designed solely for exploitation. In this paper, we build a resume screening algorithm that values exploration by evaluating candidates according to their upside potential rather than simply their estimated quality. Using data from professional services recruiting within a Fortune 500 firm, we show that this approach improves both the quality (as measured by eventual offer and acceptance rates) and diversity of candidates selected for an interview, relative to the firm's existing practices. The same is not true for traditional supervised learning based algorithms, which improve quality but select far fewer minority applicants. In an extension, we show that exploration-based algorithms are also able to learn more effectively about simulated changes in applicant quality over time. Together, our results highlight the importance of incorporating exploration in developing hiring algorithms that are potentially both more efficient and equitable.
