Open Collections

Description

We discuss prescribing optimal decisions in a framework where their cost depends on uncertain problem parameters that need to be learned from supervised data. Prescriptive analytics consists in making optimal decisions specific to a particular covariate context. Prescriptive methods need to factor in additional observed contextual information on a potentially large number of covariates as opposed to static decision methods who only use sample data. Any naive use of training data may, however, lead to gullible decisions over-calibrated to one particular data set. In this presentation, we use ideas from distributionally robust optimization and the statistical bootstrap to propose two novel prescriptive methods based on (nw) Nadaraya-Watson and (nn) nearest neighbors learning which safeguard against overfitting and lead to improved out-of-sample performance. Both resulting robust prescriptive methods reduce to tractable convex optimization problems and enjoy a limited disappointment on bootstrap data. We illustrate the data-driven decision-making framework and our novel robustness notion on a small news vendor problem as well as a small portfolio allocation problem.