Cluster-based lateral transshipments for the Zambian health supply chain

Nathalie Vanvuchelen*, Kim De Boeck, Robert N. Boute

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Many low- and middle-income countries, including Zambia, suffer from unreliable distribution of health commodities leading to high variation in service levels across health facilities. Our work investigates how transshipment can improve system-wide service levels, equity across facilities, and average inventory levels. We focus on the distribution of malaria medicines in Zambia's public pharmaceutical supply chain, which is heavily impacted by the rainy season leading to seasonality and uncertainty in demand and lead times. We use the more advanced deep reinforcement learning method Proximal Policy Optimization to develop transshipment policies and compare their performance with currently available, easy-to-use heuristics. To ensure that the model applies to settings of a realistic scale, we adopt a policy architecture that effectively decouples the policy's complexity from the problem dimensions. We find that deep reinforcement learning is mainly useful in resource-constrained environments where system-wide inventory is scarce. When sufficient inventory is available, transshipment heuristics are more appealing from an overall cost-effectiveness perspective. Based on our numerical experiments, we formulate policy insights that can support policymakers in a humanitarian health context.

Original languageEnglish (US)
Pages (from-to)373-386
Number of pages14
JournalEuropean Journal of Operational Research
Volume313
Issue number1
DOIs
StatePublished - Feb 16 2024

Keywords

  • Inventory management
  • Machine learning
  • OR in developing countries
  • Reinforcement learning

ASJC Scopus subject areas

  • General Computer Science
  • Modeling and Simulation
  • Management Science and Operations Research
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Cluster-based lateral transshipments for the Zambian health supply chain'. Together they form a unique fingerprint.

Cite this