Abstract: I work on AI for nonprofits, with nonprofits, which is actually used by nonprofits.

This talk will be focused on my line of work around iterative learning and planning. I will start with a 4-year collaboration with a crowdsourcing food rescue platform, where we combined offline ML model with online optimization to improve volunteer engagement. I will discuss our randomized controlled trial, and ongoing effort to roll it out to over 16 cities across the US.

Lifting ourselves beyond this particular application domain, we will discuss bandit data-driven optimization, a paradigm for principled iterative prediction-prescription to address the unique challenges that arise in low-resource sustainability settings. We prove theoretical guarantees for our algorithm and show that it achieves superior performance on simulated and real food rescue datasets.

I will also briefly discuss our other projects, including an NLP project in collaboration with the World Wildlife Fund which won a 2023 IAAI Deployed Application Award. I will conclude the talk with an overview of our impact and future directions.

Bio: Ryan Shi is a Ph.D. candidate of Societal Computing in the School of Computer Science at Carnegie Mellon University. He works with nonprofit organizations to address societal challenges in food security, environmental conservation, and public health using AI. His research has been deployed at these organizations worldwide. Shi studies game theory, online learning, and reinforcement learning on problems motivated by these applications. He was the recipient of a 2023 IAAI Deployed Application Award, a 2022 Siebel Scholar Award, and a 2022 Carnegie Mellon Presidential Fellowship, and was selected as a 2022 Rising Star in Data Science and ML & AI, by UChicago and USC, respectively. He has interned at Microsoft and Facebook during his Ph.D. Shi grew up in Henan, China before moving to the U.S., where he graduated from Swarthmore College with a B.A. in mathematics and computer science.

RSVP for Zoom information: https://pitt.co1.qualtrics.com/jfe/form/SV_01Tkhbj5vQeNfIW