A Possibility Frontier Approach to Diverse Talent Selection
Neil Natarajan, Kadeem Noray
TL;DR
This work tackles the computational challenge of balancing cohort diversity with talent by introducing the Selection Possibility Frontier (SPF), an algorithmic frontier linking diversity $D(c)$ and performance $P(c)$ across feasible cohorts. It proves NP-hardness of exact frontier computation, then provides a greedy, submodular-optimization-based approximation that yields a $(1-1/e)$-approximation to the true SPF, with bounds on error. The authors apply the method to a real talent program, showing that 2021–2022 finalist cohorts were Pareto-inferior relative to the frontier, while the 2023 cycle, aided by SPF, produced a cohort on the frontier, suggesting improved decision-making. Overall, SPF offers a principled, scalable tool for diagnosing inefficiencies and guiding selection toward Pareto-optimal balances of diversity and talent, with practical impact demonstrated through the case study and discussion of future work.
Abstract
Organizations (e.g., talent investment programs, schools, firms) are perennially interested in selecting cohorts of talented people. And organizations are increasingly interested in selecting diverse cohorts. Except in trivial cases, measuring the tradeoff between cohort diversity and talent is computationally difficult. Thus, organizations are presently unable to make Pareto-efficient decisions about these tradeoffs. We introduce an algorithm that approximates upper bounds on cohort talent and diversity. We call this object the selection possibility frontier (SPF). We then use the SPF to assess the efficiency of selection of a talent investment program. We show that, in the 2021 and 2022 cycles, the program selected cohorts of finalists that could have been better along both diversity and talent dimensions (i.e., considering only these dimensions as we subsequently calculated them, they are Pareto-inferior cohorts). But, when given access our approximation of the SPF in the 2023 cycle, the program adjusted decisions and selected a cohort on the SPF.