I focus on developing machine learning models that combine interpretable machine learning, Bayesian inference, predictive modeling, and causal inference.

As a part of my academic research, I developed models for predicting epileptic seizures, modeling the spread of infectious diseases, and forecasting environmental variables like the leaf area index.

Outside of academia, I’ve worked on personal projects, such as building a Bayesian hierarchical model to predict product demand for online businesses. I’m currently making Jupyter Notebook tutorials for causal inference methods, such as difference-in-differences and causal impact.

I’ve also worked on proprietary industry projects, for which I can’t share more information than that they involved predictive modeling, geospatial analysis, Bayesian inference and advanced statistical methods for econometric and market research.