Danny Pichardo

résumé and curriculum vitae

Profile

Danny Pichardo

Senior data scientist focused on applied AI, machine learning, statistics, healthcare analytics, and baseball modeling. 10+ years working with the largest healthcare datasets in the US, published registry science, leading forecast models, and back-to-back Top League Championships.

Email Danny GitHub

Experience

What I have actually built.

Senior Data Scientist / Lead GenAI Data Scientist

Blue Health Intelligence · Baltimore, MD

Jul 2020 - Present

Lead applied GenAI and data science work across healthcare use cases where model quality, governance, and practical adoption all matter.

  • Led LLM evaluation and model selection for healthcare and data science workflows, including real-world evidence and care-gap use cases
  • Built a text-to-SQL assistant with RAG over schema metadata, data dictionaries, and internal documentation
  • Developed data-analysis agents with guardrails, logging, and evaluation loops for safe use on sensitive datasets
  • Implemented an internal agent harness for coding assistants and trained researchers, analysts, and data scientists on effective usage
  • Created a longitudinal clinical journey representation and knowledge base for claims histories
  • Fine-tuned Llama 3 8B for clinical-journey tasks and scoped datasets, evaluations, and cost models for larger training runs

Senior Data Scientist

NewWave Telecom & Technologies · Elkridge, MD

May 2019 - Jul 2020

Led data science work for value-based care reporting and provider-facing analytics products tied to advanced payment models.

  • Owned the data science workstream for a provider-facing reporting dashboard
  • Built Databricks ETL and measure-calculation pipelines with validation workflows
  • Delivered predictive modeling POCs using logistic regression, XGBoost, RNNs, and claim embeddings
  • Built Looker data models and optimized SQL to meet sub-4-second dashboard performance SLAs
  • Partnered directly with UX, clinical SMEs, and engineering to translate healthcare requirements into usable systems

Statistician / Data Analysis Manager

American Urological Association · Linthicum, MD

Jan 2017 - May 2019

Statistical and computational lead for the AQUA Registry and external consulting work tied to urologic quality reporting and research.

  • Led analytic work for AQUA, a national quality registry and reporting platform
  • Designed analyses to validate EHR extraction and NLP pipelines for completeness and accuracy
  • Built predictive models for recurrence and complications across urologic procedures
  • Maintained large healthcare data assets and guided scalable data-lake implementation work
  • Coauthored published work and abstracts on registry adoption, quality metrics, and contemporary urologic practice

Independent projects

Side work with real technical substance.

Baseball forecasting

baseball-data

A modern baseball analytics repo covering ingestion, feature-store design, projection systems, and market-oriented backtesting.

  • Integrated Statcast, Retrosheet, Chadwick, and Lahman into analysis-ready layers
  • Built walk-forward predictive 5x5 projection models with Bayesian blending and interval calibration
  • Developed a repo-native prop betting framework for pricing, edge calculation, and bankroll-aware backtests

Baseball simulation

Browser-based bat-ball contact simulator

Interactive simulation app for exploring how pitch shape, timing, attack angle, and bat speed change likely batted-ball outcomes.

  • 3D pitch-flight and bat-path modeling
  • Rigid bat-ball collision model
  • Monte Carlo perturbations for sensitivity and landing-spread analysis

Technical toolkit

Breadth with a point of view.

GenAI, Agents & LLM Systems

Analytic & data science agents, execution harnesses, evaluation benchmarks, RAG, tool use, workflow design, fine-tuning, and human-in-the-loop deployment.

Statistics and modeling

Regression, predictive modeling, model comparison, calibration, walk-forward validation, causal thinking, measurement, and error analysis.

Data and platform stack

Python, SQL, Spark, Databricks, Snowflake, Azure, AWS, MLflow, Tableau, Looker, and production-minded data workflows.

Domain depth

Claims data, registry analytics, quality measures, real-world evidence, episode-based risk adjustment, healthcare operations, and baseball analytics.

Selected publications and talks

Peer-reviewed research and public speaking.

Education

Formal training.

University of Maryland, Baltimore County

B.S. in Statistics · December 2014

Working style

What collaborators can expect.

  • Start with the decision and the measurement frame, not the model pitch.
  • Use advanced methods when they improve the work, not when they merely decorate it.
  • Prefer transparent tradeoffs, strong baselines, and evaluation that survives deployment reality.
  • Build systems people can trust enough to actually use.

Contact

AI / ML / statistics / healthcare analytics

For applied AI, machine learning, healthcare analytics, or statistical systems work, reach me at pichardoda@gmail.com.

Email
pichardoda@gmail.com

GitHub
github.com/DannyPi

Get in touch Back to About Danny