I'm a graduate student at the University of Chicago applying ML models to extract behavioral signals from large social datasets using text, vision, and multimodal approaches. I received my undergraduate degree from IIT Kharagpur, where my research focused on statistical learning approaches to behavioral economics.

Here's a sample of my research on personality inference from Twitter profiles. You can find some of my language models on the Hugging Face library. A non-technical introduction to my work can be found here.

Over the last few months, I've been building an end-to-end ML pipeline to generate investment signals from of millions of call transcripts using NLP & Deep Learning at Voya Financial. It incorporates some of the latest advances in Transformer-based models to generate novel behavioral signals from text by processing billions of tokens of data.

When I'm not sampling for drift, I read non-fiction - especially philosophy and popular science. I also like photography and aviation.


You can find my resume here.

Contact Me

You can contact me on LinkedIn or at:

partha s kadambi <at> gmail.com