Bootstrap Robust Prescriptive Analytics

TL;DR

This paper introduces a robust prescriptive analytics framework that combines bootstrap methods with robust optimization to improve out-of-sample decision quality in uncertain, data-driven settings.

Contribution

It proposes a novel robust prescriptive approach using bootstrap-based robust optimization, ensuring better generalization and reduced overfitting in data-driven decision-making.

Findings

Robust methods outperform nominal ones on synthetic bootstrap data.

The approach reduces to convex optimization problems for local learning methods.

Application to a newsvendor problem demonstrates effectiveness.

Abstract

We address the problem of prescribing an optimal decision in a framework where the cost function depends on uncertain problem parameters that need to be learned from data. Earlier work proposed prescriptive formulations based on supervised machine learning methods. These prescriptive methods can factor in contextual information on a potentially large number of covariates to take context specific actions which are superior to any static decision. When working with noisy or corrupt data, however, such nominal prescriptive methods can be prone to adverse overfitting phenomena and fail to generalize on out-of-sample data. In this paper we combine ideas from robust optimization and the statistical bootstrap to propose novel prescriptive methods which safeguard against overfitting. We show indeed that a particular entropic robust counterpart to such nominal formulations guarantees good performance on synthetic bootstrap data. As bootstrap data is often a sensible proxy to actual out-of-sample data, our robust counterpart can be interpreted to directly encourage good out-of-sample performance. The associated robust prescriptive methods furthermore reduce to convenient tractable convex optimization problems in the context of local learning methods such as nearest neighbors and Nadaraya-Watson learning. We illustrate our data-driven decision-making framework and our novel robustness notion on a small newsvendor problem.