Researcher. Leader. Entrepreneur.

My research work lies at the intersection of Machine Learning and the social sciences. I have an active research agenda in Natural Language Processing, Network Reconstruction, and Attribute Selection. I am pursuing applications across Information Processing, Asset Pricing, Corporate Finance, Philosophy, Media and more. I am keen to collaborate on a variety of problems and domains–so please reach out!

Research Publications

“The Creative Machine" (2017)
Proceedings of the 8th International Conference on Computational Creativity (143-151)
“Disambiguation and Prediction of Dynamic Hierarchical Data Structures” (2017)
U.S. Patent No. 273002AE
"Large, Noisy, Unstructured Textual Data." (2017), Part 1, Doctoral Research Studies, Jožef Stefan International Postgraduate School, Ljubljana, Slovenia,
“Table Understanding from Text Documents” (2016)
Encyclopedia of Machine Learning (Springer)
“Unsupervised Techniques for Extracting and Clustering Complex Events in News” (2013)
Proceedings of the North American ACL Conference (with D. Rusu and A. Kimball)
“A System and method for Interactive Machine Translation” (2012)
U.S. Patent No. 9,613,026
“Effective Machine Translation for Real-World Translators” (2009)
Proceedings of the International Translating and the Computer Conference (with A. Eisele, C. Federmann)
"Consciousness as the Domain of a Computation" (2009)
Logos: Cornell Journal of Philosophy

Popular Publications

"How to Make Your Company Machine Learning Ready," (2016)
Harvard Business Review

Working Papers

“A Distributed Information Verification Model for Financial Markets” (with R. Olsen)
“Discovering Hierarchical Structure from Bags of Paths”
“Trading on Talent: Human Capital and Firm Performance.” (with A. Fedyk)
“When Can the Market Identify Stale News?” (with A. Fedyk)
Peer-reviewed conferences:
Trans-Atlantic Doctoral Conference 2015; World Finance Conference 2015.
"The Career Consequences of Corporate Scandals." (with A. Fedyk)
"Asymmetric Peer Group Learning for Network Time Series Prediction." (with J. Erett)

Research Agenda

Work that is at various stages of completion, without a full paper having yet been written. Often some preliminary versions of this research have been presented at seminars and discussed with relevant colleagues in the field. Coming soon: gender in the workplace; global workforce dynamics and skills; the career consequences of corporate scandals; entrepreneurship; a natural language attribute selection framework; understanding SEC filings; a general purpose resume parsing framework.