Amahle is pregnant and soon expecting a new addition to her family. She has been seeking maternal care through South Africa’s national WhatsApp helpline for the past seven months where she frequently consults a help-desk team about pregnancy challenges she’s been facing. At one point she got really worried that she couldn’t feel her baby move and it took a while for the help-desk to get back to her. Soon, she will be able to get instant recommendations with the help of a technology developed by IDinsight that will automatically answer her questions.
We were recently approached by a government to optimally allocate teachers to schools. The state has a few hundred secondary schools and is meant to offer a set of subjects in all these schools. But there are a number of classrooms without a teacher allocated. To close these “gaps”, a new cohort of teachers were trained to join the existing set of teachers. They asked us how these new teachers should be assigned while taking operational and logistical constraints into account. These kinds of problems are notoriously hard to solve optimally1. Operational Research offers clever techniques to search the solution space for optimal solutions.
In this post, I discuss how IDinsight’s DSEM team implemented a data quality check for pairs of variables displaying linear relationships. We explain why we chose a Bayesian model, and the tweaks we made to address the hierarchy and outliers in data. We will also see how to implement the model using PyMC3.
