Dr. Santiago Calderón is a senior research economist in the national economic accounts research group at the U.S. Bureau of Economic Analysis. Before joining the federal statistical system, he had years of experience in the private sector as a research scientist at various companies. Bayoán also held academic appointments with the Biocomplexity Institute and Initiative at the University of Virginia, where he started his career in public service.
His research has centered on improving decision-making. His transdisciplinary research approach has enabled him to routinely collaborate across disciplines and develop a diverse set of domain knowledge and methodological toolset. He also participates in various open-source software communities (e.g., JuliaLang) and civic activism (e.g., Code4PR, Mentes Puertorriqueñas en Accion).
My work sits at the intersection of economics, public policy, and computational methods. I have developed research around official statistics, digital economy measurement, and the use of data-intensive methods to inform evidence-based decisions.
I am especially interested in building reproducible analyses and open-source tools that make complex questions more transparent and actionable.
- Published research on national economic accounts and measurement issues, primarily focusing on intellectual property products (IPPs), such as software and data assets.
- Contributed to official statistics through innovative methodologies and operational enhancements. Some examples include the use of big data, natural language processing (NLP), and machine learning, implemented in Python, R, Julia, MATLAB, and Stata.
- Collaborated and engaged with stakeholders, including members of international expert groups and policymakers.Research on digital economy measurement, intellectual property products, own-account software, and data assets in national accounts.
- Provided government clients consulting services in the areas of science policy, labor economics, computational models, and program evaluation through problem identification, data discovery (inventory, screening, acquisition), data ingestion, data wrangling (profiling, preparation, linkage, and exploration), fitness-for-use assessment, statistical modeling, and analysis.
- The work employed high-performance computing (HPC) environment and tools like Slurm, Git, containers, and databases (PostgreSQL) to store and access billions of records, some collected through APIs (e.g., REST, GraphQL) that were used in natural language processing (NLP), geographic information systems (GIS), agent-based modeling (ABM), graph theory, and regression analysis using SQL, Julia, and R.
- Led and supported interdisciplinary public-sector analytics projects, including open-source software measurement, workforce studies, and public safety evaluation.
- Developed the statistical components for the mass-scale residential building energy benchmarking used in demand side management (DSM). The work leveraged various data sources, including real estate information, government administrative records (e.g., building footprint, zoning), weather records, geographic information systems (GIS) layers, and utility meter data. Some of the technologies employed include APIs, databases (SQL), and R.
- Delivered commissioned reports and analyses related to program evaluations of building policies and energy use programs in California.
- Conducted neuroeconomic studies, encompassing aspects of study design, recruitment, experimentation, and data analysis, included in published academic articles.
- Collected and analyzed biometric data, including EDA/GSR, EEG, ECG, and eyetracking, using iMotions.