Bio
I’m a Policy Data Scientist specializing in causal inference and machine learning for public policy evaluation. Master’s candidate at Pontificia Universidad Católica de Chile researching natural resource economics and social conflict, with 4+ years at Peru’s Ministry of Education developing data infrastructure for evidence-based policy decisions.
I combine applied economics research, open-source software development, and public policy evaluation to democratize access to economic data and inform intervention design across Latin America.
Research & Technical Expertise
Current Research | Examining how extractive industries affect human capital accumulation in mining communities using spatial econometrics and difference-in-differences methods.
Open Source | Creator of enahodata, usebcrp, usecasen, and usebcch — Python and Stata packages providing standardized access to household surveys and central bank data across Latin America.
Stack | Python (pandas, scikit-learn, geopandas), Stata, R (tidyverse, sf), SQL, Git, Quarto, Docker
View my research portfolio · Explore my software · Read my blog