Tackling poverty in Togo with machine learning and non-traditional big data w/ Emily Aiken

In this episode of the podcast, Lily Adelstein and Emily Aiken discuss the paper, "Machine learning and phone data can improve targeting of humanitarian aid". 

Emily Aiken is a PhD student at the UC Berkeley School of Information advised by Joshua Blumenstock. Emily is interested in the application of computational methods to issues of economic development, global health, and sustainability. She is currently working on expanding machine learning methods for estimating poverty and other measures of well-being from digital trace data. Her past research has included deep learning methods for tracking disease outbreaks using Internet-based data sources and identifying missing people in social media streams using techniques from computer vision. She received her B.A. in computer science from Harvard University, and is the recipient of a 2022-2024 Microsoft Research PhD Fellowship.

Website: https://emilylaiken.github.io/