I am a Ph.D. Candidate at the Vanderbilt University School of Engineering and a Research Fellow at Vanderbilt Law School’s Program on Law & Innovation. I conduct research on machine learning, law and policy.
“Text Modeling for Understanding and Predicting the Federal Government.” Invited Talk at 2016 INFORMS Annual Meeting.
Email: john dot j dot nay at gmail dot com
- “Predicting and Understanding Law with Machine Learning.” Data Science D.C. August Presentation at George Washington University, Washington D.C.
- “Distributed Representations of Institutions and Their Policy Text” June Presentation at International Conference on Computational Social Science, Evanston, IL.
- “Modeling Text for Legal Prediction and Analysis” May Presentation at Gruter Institute for Law & Behavioral Research Annual Conference, Lake Tahoe, CA.
- “Natural Language Processing for Large Legal Databases” April Presentation at the Workshop on Frontiers of Artificial Intelligence and the Law.
- “Predicting and Understanding Human Cooperation” March Presentation at Vanderbilt Microeconomics Seminar.
- “Forecasting Agricultural Productivity with Remote Sensing and Machine Learning”, March Presentation at Annual Meeting of National Science Foundation Water Sustainability and Climate Investigators, Arlington, VA.
- “Data-Driven Dynamic Decision Models” December Presentation at the 2015 Winter Simulation Conference, Huntington Beach, CA.
- “An R Package for Data-Driven Decision Modeling” October Presentation at Nashville R Users Group.
Websites for my open-source software pacakges:
- datafsm: Estimating Finite State Machine Models from Data
- forecastVeg: Python Scripts for Forecasting Vegetation Health
- predMarket: A Climate Prediction Market Simulation Model
- sa: Sensitivity Analysis for Complex Computational Models
- eat: Empirical Agent Training Software for Data-Driven Modeling
- agp: Agent Gentic Programming Software for Data-Driven Modeling