Africa (Proceedings of the National Academy of Sciences 2013): USAID and the UN's World Food Program have proposed strategies for allocating ready-to-use (therapeutic and supplementary) foods to children in developing countries. Analysis is needed to investigate whether there are better alternatives. We use a longitudinal data set of 5657 children from Bwamanda to construct a statistical model that tracks each child's height and weight throughout the first five years of life. We embed this model into an optimization framework that chooses which individual children should receive food based on a child's sex, age, height and weight, to minimize the mean number of disability-adjusted life years per child subject to a budget constraint. Our proposed policy compares favorably to those proposed by the aid groups. Time permitting, we will also discuss a recent analysis of a nutrition program in Guatemala that quantifies the age dependence in the impact of supplementary food, and develops a food allocation policy that exploits this age dependence and reduces child stunting.
India: Motivated by India's nationwide biometric program for social inclusion, we analyze verification (i.e., one-to-one matching) in the case where we possess 12 similarity scores (for 10 fingerprints and two irises) between a resident's biometric images at enrollment and his biometric images during his first verification. At subsequent verifications, we allow individualized strategies based on these 12 scores: we acquire a subset of the 12 images, get new scores for this subset that quantify the similarity to the corresponding enrollment images, and use the likelihood ratio to decide whether a resident is genuine or an imposter. Compared to the policy currently used in India, our proposed policy provides a five-log (i.e., 100,000-fold) reduction in the false reject rate while only increasing the mean delay from 31 to 38 seconds.
A full speaker bio is available on CISAC's website.