Decision-Aware Learning for Optimizing Health Supply Chains

TL;DR

This paper introduces a scalable, decision-aware machine learning approach that improves health supply chain optimization by aligning demand prediction with decision-making, significantly reducing unmet medical needs in Sierra Leone.

Contribution

It proposes a novel Taylor expansion-based loss function for decision-aware learning, integrated into scalable models like random forests, to enhance supply chain decisions in developing countries.

Findings

Significantly reduced unmet demand in Sierra Leone health facilities.

Demonstrated scalability and flexibility of the approach with large datasets.

Improved allocation efficiency through end-to-end demand prediction and optimization.

Abstract

We study the problem of allocating limited supply of medical resources in developing countries, in particular, Sierra Leone. We address this problem by combining machine learning (to predict demand) with optimization (to optimize allocations). A key challenge is the need to align the loss function used to train the machine learning model with the decision loss associated with the downstream optimization problem. Traditional solutions have limited flexibility in the model architecture and scale poorly to large datasets. We propose a decision-aware learning algorithm that uses a novel Taylor expansion of the optimal decision loss to derive the machine learning loss. Importantly, our approach only requires a simple re-weighting of the training data, ensuring it is both flexible and scalable, e.g., we incorporate it into a random forest trained using a multitask learning framework. We apply our framework to optimize the distribution of essential medicines in collaboration with policymakers in Sierra Leone; highly uncertain demand and limited budgets currently result in excessive unmet demand. Out-of-sample results demonstrate that our end-to-end approach can significantly reduce unmet demand across 1040 health facilities throughout Sierra Leone.