Timezone: »

 
Poster
Making the Cut: A Bandit-based Approach to Tiered Interviewing
Candice Schumann · Zhi Lang · Jeffrey Foster · John Dickerson

Thu Dec 12 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #85
in Applications -- Computational Social Science »

Given a huge set of applicants, how should a firm allocate sequential resume screenings, phone interviews, and in-person site visits? In a tiered interview process, later stages (e.g., in-person visits) are more informative, but also more expensive than earlier stages (e.g., resume screenings). Using accepted hiring models and the concept of structured interviews, a best practice in human resources, we cast tiered hiring as a combinatorial pure exploration (CPE) problem in the stochastic multi-armed bandit setting. The goal is to select a subset of arms (in our case, applicants) with some combinatorial structure. We present new algorithms in both the probably approximately correct (PAC) and fixed-budget settings that select a near-optimal cohort with provable guarantees. We show via simulations on real data from one of the largest US-based computer science graduate programs that our algorithms make better hiring decisions or use less budget than the status quo.

Keywords: Bandit Algorithms · Computational Social Science · Applications · Algorithms
[ Paper]  [ Poster] 

Author Information

Candice Schumann (University of Maryland)
Zhi Lang (University of Maryland, College Park)
Jeffrey Foster (Tufts University)
John Dickerson (University of Maryland)

More from the Same Authors