Experience and Education
Senior Data Science Engineer, SimSpace
Principal Data Scientist, Geneia
Medical Science Liaison (MSL), Rheumatology, Bristol-Myers Squibb
Medical Science Liaison (MSL), Neurology, EMD Serono
University of Pennsylvania, Philadelphia, PA, Ph.D., Neuroscience
Professional Outlets
AI and Bias In Healthcare – a video discussion about social bias in artificial intelligence and how to address it
AI interpretability is especially critical in healthcare – a blog post about model interpretability
Model interpretability and healthcare – highlights from a podcast about data science, model interpretability, COVID-19, and healthcare
Personal Projects
State-Space Models: Learning the Kalman Filter – Different research fields may speak different mathematical languages. There’s nothing like rigorous software testing for accurate translation. Go here for the code.
Beyond Point Estimates – When we need to predict more than just a mean or a median, full posterior distributions from Bayesian models are often the way to go. But sometimes, that’s too computationally intensive and we need some shortcuts. Quantile regression is a handy alternative. For even more efficiency, we can use multi-task learning so that a single model produces all the quantiles we want. Go here for the code.
Weather and climate API – Using mock testing and FastAPI to query, create, and test web APIs. Go here for the code.
Pandas vs. Polars, Python vs. Rust: Who will win? – Benchmarks are nice, but how fast are our favorite data tools on realistic data workflows? Go here for the code.
Bayesian Updating with a Beta-Binomial Model: Basketball Edition – We start the season thinking our team is this good (or bad). But as the wins and losses pile up, how do we update our priors? Go here for the code.
Bayesian Updating with a Dirichlet-Multinomial Model: Visualizing More Outcomes – As we add outcomes to our model, the concepts stay the same but the dynamics grow more complex. Viewing animations of the model can help us develop intuitions about how it works. Go here for the code.
Investment Performance Metrics Dashboard – Plotly Dash app for tracking profit/loss and other investment performance per transaction or over time. Go here for the code.
Monitoring Data Pipelines with Airflow and Tcl/Tk – Airflow is terrific for scheduling and monitoring data pipeline components. But we also want to monitor in real-time what’s happening inside those components. Go here for the code.
Add Columns to Polars Dataframes Quickly – There are straightforward, slow ways to do things, and then there are faster ways. Know how to choose. Go here for the code.
Deep Reinforcement Learning and Rainbow – How does a computer learn to play video games?
Information Theory for Toddlers – A low-entropy bedtime story
SHAP Tutorial – How do we use Shapley values to interpret machine learning models? Go here for the code.
Case Study: How to Translate a Healthcare Problem into a Predictive Modeling Problem – How do we correctly select cases for our training data?
The Peanuts Project – Charlie Brown, Snoopy, Lucy, Linus . . . who was the most important character? Which of their relationships was the strongest? Indulge some nostalgia and hum some Guaraldi!
Classifying Medicine – How do patients experience conventional and alternative medicine differently? Yelp, random forests, ROC curves, and so much more!
Recent posts
Recent posts, mostly links to interesting articles that I have been reading:
- What I Read: impossible languageshttps://www.quantamagazine.org/can-ai-models-show-us-how-people-learn-impossible-languages-point-a-way-20250113/ Can AI Models Show Us How People Learn? Impossible Languages Point a Way.Ben Brubaker1/13/25 11:00 AM “Certain grammatical rules never appear in any known language. By constructing artificial languages
- What I Read: Statistical Intuitions
- What I Read: transfer learninghttps://lunar-joke-35b.notion.site/Transfer-Learning-101-133ba4b6a3fa800e8cede11ee3f1c1cd Transfer Learning 101Himanshu DubeyNov 5, 2024 “Let’s understand Transfer Learning in greater detail.”
- What I Read: Model Merginghttps://planetbanatt.net/articles/modelmerging.html Model Merging and YouEryk BanattAugust 2024 “Model Merging is a weird and experimental technique which lets you take two models and combine them together to get a new model.”
- What I Read: optimizing softmaxhttps://maharshi.bearblog.dev/optimizing-softmax-cuda Learning CUDA by optimizing softmax: A worklogMaharshi Pandya04 Jan, 2025 “Optimizing softmax, especially in the context of GPU programming with CUDA, presents many opportunities for learning.”
- What I Read: agents
- What I Read: Age of Data
- What I Read: ScyllaDBhttps://medium.com/@abdurohman/mind-blowing-postgresql-meets-scylladbs-lightning-speed-and-monstrous-scalability-7dcda1eb1cea Mind-blowing: PostgreSQL Meets ScyllaDB’s Lightning Speed and Monstrous ScalabilityAbdurohmanDecember 24, 2024 “While PostgreSQL excels in many use cases, our experience shows that for write-heavy, high-scale operations, the distributed architecture
- What I Read: Building agents
- What I Read: Shapley Interactions
Browse posts
- April 2025
- March 2025
- February 2025
- January 2025
- December 2024
- November 2024
- October 2024
- September 2024
- August 2024
- July 2024
- June 2024
- May 2024
- April 2024
- March 2024
- February 2024
- January 2024
- December 2023
- November 2023
- October 2023
- September 2023
- August 2023
- July 2023
- June 2023
- May 2023
- April 2023
- March 2023
- February 2023
- January 2023
- December 2022
- November 2022
- October 2022
- September 2022
- August 2022
- July 2022
- June 2022
- May 2022
- April 2022
- March 2022
- February 2022
- January 2022
- December 2021
- November 2021
- October 2021
- September 2021
- August 2021
- July 2021
- June 2021
- May 2021
- April 2021
- March 2021
- February 2021
- January 2021
- December 2020
- November 2020
- August 2020