Maxfield Frohlich
Principal Data Scientist
San Jose, California, United States
Summary
🤩
Rockstar🎓
Top SchoolMaxfield Frohlich is a Principal Data Scientist in San Jose with 7 years of experience turning complex healthcare and finance problems into automated, decision-ready analytics. At Genentech he advises capital allocation of over $500M in reserves, improved reserve forecasting to free $6M, and deployed an 80%‑accurate NLP contract classifier into production. He is an active open-source contributor to the popular sktime time-series library, adding fault-tolerant features like FallbackForecaster and an ExpandingCutoffSplitter that mirror production backtesting needs. His background spans HEOR, EHR/claims analytics, and cloud model deployment (SageMaker/Glue/Athena), combining research rigor with pragmatic engineering. Maxfield excels at turning messy clinical and financial data into reproducible pipelines and actionable dashboards that drive measurable business impact.
8 years of coding experience
6 years of employment as a software developer
San José State UniversityMaster of Arts - MA, Medical Science, Master of Arts - MA, Medical Science at Loyola University ChicagoSan Diego State University
Github Skills (10)
scikit10
scikit-learn10
forecasting10
pandas10
machine-learning10
forecast10
time-series10
pytest10
python10
testing10
Programming languages (3)
Github contributions (5)
sktime/sktime
Jan 2024 - Oct 2024
A unified framework for machine learning with time series
Role in this project:
Data Scientist
Data ScientistContributions:24 reviews, 11 PRs, 88 comments in 9 months
Contributions summary:Maxfield primarily contributed to the `sktime` repository, which focuses on machine learning with time series. Their work involved addressing deprecation warnings in the `EnsembleForecaster` related to `pd.DataFrame.groupby`, enhancing the `FallbackForecaster` by adding a `predict_interval()` option and a `nan_predict_policy`, and fixing a bug related to the `ExpandingCutoffSplitter`. The contributions demonstrate a focus on improving the robustness, functionality, and stability of the forecasting models within the library. Furthermore, the user added a new splitter to provide flexibility in time series analysis.
forecastingtime-series-analysistime-series-regressiondata-sciencedeep-learning
ninedigits/sktime
Jan 2024 - Oct 2024
Contributions:39 pushes, 10 branches in 9 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.