Data for Democracy is an international community of data professionals, trying to be helpful and bring about positive change. I am leading a team of 5-10 data scientists to analyze data coming from India’s National Family Health Survey. Conducted every ten years, these questionnaires provide rich datasets combining individual and family health, and household characteristics. We are mainly looking at women’s empowerment issues, for example trying to predict the sex of the reported head of the household from household characteristics.

The collaboration is playing out on our D4D Github project repo. We are using Slack to communicate and data.world to share data. My responsibilities have included: generating the idea and interest; building the repo, Slack channel, and data.world site; and coalescing teams.