Machine Learning for a More Efficient Supply Chain
Drew Arenth, Benjamin Fels, and Suvrit Sra of macro-eyes in the U.S. will use statistical machine learning applied to supply chain and immunization data at health facilities in Tanzania to better predict demand and avoid the delivery of the incorrect quantity or selection of vaccines. The aim is to minimize waste and maximize childhood vaccination coverage. They will work with NGOs and regional medical offices to identify two pilot sites and gather site-specific supply chain data. The data will be used to train and test algorithms that will learn to identify predictive patterns to forecast demand and recommend the optimal delivery of vaccines to each site. Predictions will be sent to pilot health clinics via SMS to determine their accuracy. Health worker insight on populations and demand, conveyed via SMS, will programmatically augment the analysis of supply chain and immunization data.