Creating a Next-Generation Financial Dataset from Scratch with NLP and Active Learning

Patrick Harrison July 6, 2019 Talks

I was delighted to be invited to give a talk at the inaugural spaCy IRL conference in Berlin, Germany. spaCy IRL was a gathering of researchers and practitioners pushing the boundaries of industrial-strength natural language processing with the spaCy software library and ecosystem.

My talk highlighted one of my group’s projects: using natural language processing and active learning to create a new kind of financial intelligence data. The goal was to assemble a dataset about companies’ environmental, social, and governance practices (“ESG”). We used a human-in-the-loop workflow to iteratively train and validate machine learning models to detect mentions of companies’ ESG practices from publicly-available documents. Check out the video to learn more about our methodology.

The slides from the talk are available below.

Up next

Analytics Panel Discussion with Pittsburgh Data Science I was happy to join the Pittsburgh Data Science Group for a panel discussion about how local technology leaders are applying advanced analytics within their teams and businesses.

Previously

Managing Data Science in the Enterprise Josh Poduska, Chief Data Scientist at Domino Data Lab, and I teamed up to talk about how to manage data science as an organizational capability, the data science project lifecycle, common organization structures for data science teams, and more at the Strata Data Conference in New York.