Daniel Silva-Inclan

Daniel Silva-Inclan

Data Science Manager

EY

Biography

Hi, I’m Daniel Silva-Inclan, and I’m open to new opportunities in data science and data engineering.

With 7+ years of experience as a researcher, data scientist, and data engineer, I specialize in turning complex challenges into tractable ML, AI, statistical, and economic problems and delivering analytics solutions that scale. These days, I’m at EY, where I help teams design, develop, and deploy enterprise-grade systems – from GenAI document-intelligence pipelines to cloud-native ETL workflows built on Databricks, Snowflake, and Azure.

My roots are in economic research. At the IMF and the Becker Friedman Institute at UChicago, I built optimization frameworks and synthetic data tools that made economic modeling faster, more reliable, and more reproducible.

My technical toolkit includes Python (pandas, sklearn, dbt, streamlit), R (tidyverse, shiny, leaflet, data.table), SQL, Docker, and cloud platforms like Azure (AI Foundry, MLflow, CosmoDB), Snowflake, and Databricks, with additional experience in Go, C/C++, and Julia. I’m always exploring new tools and frameworks to stay ahead.

Outside of work, you’ll find me tinkering with my home automation setup, self-hosting cloud services (home movies and my photography), experimenting with sous-vide and smoker recipes, or plotting my next strategic win in Age of Empires II: DE as I climb back to top 10%.

Interests

  • Optimization and Metaheuristics
  • Causal Inference (with ML and econometrics)
  • Differential Privacy
  • Sous-vide cooking

Education

  • M.S. in Computer Science with Specialization in High-Performance Computing, 2020

    University of Chicago

  • B.S. in Statistics; B.A. in Economics, 2016

    University of Chicago

Experience

 
 
 
 
 

Projects Officer

International Monetary Fund (IMF)

Apr 2021 – Present Chicago

Research Department under Chief Economist and Research Director Gita Gopinath, Assistant to the Director Emine Boz, and Economist Suman Basu.

  • Developed a research pipeline to quickly analyze and diagnose multiple equilibria issues in each new proposed economic model – increasing research throughput (model iteration) from weeks to days and improving robustness of the research process.
  • Built a parallelized 2-stage multistart optimization in Python and high dimensional diagnosing visualizations in R to develop previously mentioned research pipeline.
  • Expanded development of the Integrated Policy Framework: the IMF’s conceptual model for optimal monetary policy, capital controls, foreign exchange intervention, and macroprudential policy in the context of COVID-19.
 
 
 
 
 

Research Assistant

Becker Friendman Institute

Jun 2018 – Present Chicago

Research assistant in the Open Source Economics Lab group for Dr. Richard W Evans.

  • Researched private and synthetic data generation process, and data deanonymization of sensitive tax data (PUF) in the context of differential privacy, k-anonymity, and Bayesian networks.
  • Developed pipelines for private and synthetic data generation processes in R
  • Prototyped ML-based error correction pipeline for editing tax documents for the Internal Revenue Services (IRS) in Python.
 
 
 
 
 

Data Scientist

Civis Analytics

Sep 2016 – Sep 2017 Chicago

Research and Development Causal Inference team.

  • Developed and presented a snack advertisement pipeline for a Fortune-50 food company and Boston Consulting Group to cluster and visualize customer segmentation and determine opportunities for digital advertisement.
  • Prototyped media-mix pipeline to verify effectiveness of Verizon digital marketing campaigns through heterogeneous treatment effect modeling.
  • Researched and developed geospatial capabilities including a pipeline for spatial analysis (R, Python, QGIS, PostgreSQL), and an interactive map plotting tool for internal and external use.
 
 
 
 
 

Research Assistant

University of Chicago

Apr 2016 – Sep 2016 Chicago

Research Assistant for Dr. Victor Lima, Dr. Aryal Gaurab, and Dr. John List.

  • Simulated Shapley-Shubix and Banzahf power indices in R to analyze strength of political coalitions within the Chilean Government.
  • Simulated a nonparametric price discrimination model in Matlab and R where consumers have multidimensional private information on several goods.
  • Performed data entry and cleaning in Excel for major field experiment conducted in Chicago on the economics of early childhood interventions.