CHRISTIAN
CALLAHAN
Data / ML Engineer
I build models that hold up to scrutiny, end to end: leakage-safe labeling, real baselines, calibration, and a clear line between synthetic and real data. Every metric is committed and reproducible from a clean clone. From SQL and warehouse modeling to the Streamlit, FastAPI, or Next.js interface on top.
What I Build
Models that hold up to scrutiny, shipped end-to-end.
Statistically Honest
Leakage-safe labeling, baselines before boosting, cross-validation, bootstrap CIs, and calibration. The numbers mean what they say.
End to End
Raw data and SQL, through tuned and calibrated models, to a Streamlit, FastAPI, or Next.js interface.
Reproducible by Default
Synthetic and real data kept separate, every metric committed and runnable from a clean clone.
Stack
Portfolio
A few things I've shipped
Pit Wall Intelligence
Ingested 4 seasons of lap-level F1 data (85 races, 90k laps, 33 circuits) through a DuckDB + dbt warehouse. Trained an isotonic tyre-degradation model (1.38s within-circuit MAE; 9.4s leave-one-circuit-out median) and a calibrated LightGBM undercut classifier (AUC 0.66 ± 0.05 on 5-fold GroupKFold, Brier 0.084). Validated a Monte Carlo race simulator against 3 famous 2024 strategy calls (Monaco / Hungary / Italy); average MAE 1.65 finishing positions. Shipped a 6-page Streamlit dashboard, a containerized FastAPI inference service (17ms median latency), and a weekly automated retraining workflow with MLflow tracking.
SignalForge
Logistic regression vs. random forest vs. gradient boosting on IBM Telco (7,043 customers), with leak-free cross-validation, bootstrap 95% CIs, paired t-tests, and calibration. The models land within ~0.003 AUC with overlapping CIs, so the writeup treats selection as a calibration/interpretability decision rather than an accuracy contest.
SaaS Churn Simulator
Time-windowed (observation / gap / check) labeling on RetailRocket (2.76M events, 1.41M visitors); LightGBM (Optuna-tuned, isotonic-calibrated) vs. a logistic baseline, plus a budget-targeting ROI simulator. 5-fold CV ROC-AUC 0.88 ± 0.06; calibration cut the test Brier score from 0.065 to 0.009.
Ecommerce Retention & Growth
30-day churn prediction on the WSDM KKBox dataset: calibrated XGBoost (PR-AUC and calibration emphasized under ~9% churn), K-Means LTV segmentation, and a retention-ROI simulator. Ships a synthetic generator so the pipeline runs without the large download.
Ticket Intel
Routing and extractive summarization on Banking77 (77 intents) using TF-IDF + Naive Bayes by design: fast, cheap, interpretable, with the router abstracted so a transformer can drop in later.
Experience
My professional and educational journey
Founder & Principal
CGC Labs
2026 - Present
Healthcare BI for community and rural hospitals
Outsourced BI for rural and critical access hospitals. Executive dashboards on whatever the hospital already runs (Tableau, Python/Streamlit, Excel), plus SQL operations on the existing EMR. The system I built in-house, now a managed service.
Key Impact
executive dashboards in Tableau, Python/Streamlit, or advanced Excel, built on existing EMR sources with no new licenses
a proven healthcare BI system, developed at critical access hospitals, now offered as a turnkey managed service
healthcare BI for community and rural hospitals, the segment large firms ignore
Business Intelligence Analyst
Community Hospital (Critical Access)
2022 - 2026
McCook, NE
Owned the BI function at a critical access hospital. Replaced a failed $150K vendor solution with custom Tableau and SQL infrastructure. Did the BI-side data transformation on the Veradigm-to-Paragon EMR migration, alongside Altera. Built the reporting that survived CMS audit.
Key Impact
first-ever 75th percentile HCAHPS ranking for the facility
custom Tableau/SQL system delivering $10K/yr in ongoing savings
BI-side data transformation on the Veradigm-to-Paragon cutover, alongside Altera; reporting kept intact
quality, risk, and operational analytics embedded in clinical workflows
Education
Dual MBA & M.S. Data Science
Eastern University
Expected 2027Bachelor of Applied Science
Peru State College
2022Recent Activity
Continuous learning and shipping.
Latest Commits
Loading commits...
Current Focus
F1 Strategy Analytics
Pit Wall Intelligence — tyre degradation, undercut probability, and Monte Carlo race simulation over a DuckDB + dbt warehouse and calibrated ML. My most advanced project, end-to-end: warehouse, models, a 6-page dashboard, and a Dockerized FastAPI service.
Churn & Retention Modeling
Churn and retention modeling with statistical rigor — leakage-safe labeling, calibration, and bootstrap confidence intervals across SignalForge and the SaaS Churn Simulator.
Connect
Open to data and ML engineering roles. Email is fastest; the code is on GitHub, the history is on LinkedIn.
christian.g.callahan@gmail.com