Welcome

Researching machine learning, finance, markets, and climate change.

Twitter: @johnjnay

Publications on machine learning applied to climate change:

• Climate-contingent finance
• Computational simulation modeling of trader behavior in climate prediction markets
• Machine-learning approach to forecasting remotely sensed vegetation health
• Application of machine learning to prediction of vegetation health
• Decision-support computational models for climate change adaptation
• Empirically-grounded simulation model of impact of climate forecasts on agricultural income
• Agent-based simulation model of the influence of climate forecast accuracy on farmer behavior
• Participatory simulation modeling of urban flooding for decision support
• Modeling agricultural response to drought in the U.S.
• Hierarchical Bayesian modeling of urban water policy
• Qualitative and quantitative analysis of drought, risk, and politics

Publications on machine learning applied to policy:

• Natural language processing and machine learning for law & policy
• Predicting law-making with machine learning
• Natural language processing of presidential documents, with a deep dive on environmental policy
• Gov2Vec: Machine learning distributed representations of government institutions
• Deriving the market’s political predictions with policy impact indices constructed with machine learning
• The big shift: From monetary to fiscal policy

Publications on machine learning applied to decision-making:

• Generalizability: Machine learning and humans-in-the-loop for decision systems
• Predicting human cooperation with machine learning
• Automatically estimating models of decision-making with machine learning

Open-source software packages:

• datafsm: Estimating Decision-making Models with Machine Learning
• forecastVeg: Forecasting Vegetation Health with Machine Learning
• 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

Coverage of some of my research in Science.