Real-time data selection and ordering for cognitive bias mitigation

Abstract

We consider the problem of selecting and ordering a subset of N' out of N observations to be presented to a human being in the context of a binary hypothesis testing problem. We restrict our attention to i.i.d. Gaussian observations. We propose an extension of the approximate subset sum algorithm, and show that it can be used to solve the problem with polynomial complexity. Furthermore, we show that the solution yields near optimal detection performance when compared to the case where all N observations are optimally processed.