HOME
IntroSkillsPortfolioExperienceContact

CHRISTIAN

CALLAHAN

I build production ML systems that quantify business impact — churn prediction, revenue optimization, and decision intelligence with statistical rigor.

PROJECTSCONTACT

What I Build

Systems that predict behavior and drive decisions.

Churn Prediction

Predict which customers will leave before they do. LightGBM, XGBoost, and uplift modeling to target retention spend where it matters.

Revenue Optimization

Customer lifetime value modeling, ROI simulators, and budget optimization. Turn model outputs into dollar figures stakeholders understand.

Decision Systems

NLP pipelines for ticket routing, automated reporting infrastructure, and production ML systems. Built for speed and reliability.

Portfolio

A glimpse of the projects I've been working on

Featured Project

SignalForge

Churn prediction with statistical rigor. Optuna-tuned LR at 0.849 AUC with 5-fold CV and bootstrap CIs. Quantified $1.67M revenue at risk and built a retention ROI framework. The interesting finding: simple models beat ensembles.

PythonScikit-learnUplift ModelingCausal Inference

Ticket Intel

NLP pipeline for routing support tickets, summarizing threads, and extracting entities. Built for speed — 12ms p99 latency, 500+ req/sec. Uses TF-IDF + Naive Bayes instead of LLMs because 'refund please' doesn't need GPT-4 to classify. 90% F1 across 5 categories.

PythonFastAPIspaCyStreamlit

SaaS Churn Simulator

Predicts which customers will churn and which retention offers work. LightGBM on 2.7M events achieves 0.85 AUC and 3.2x lift. Live ROI calculator shows budget impact before you spend.

PythonLightGBMMLflowDocker

AutoModeler

Auto-generates 3-statement financial models from public data. Pulls from Financial Modeling Prep API, projects 5 years forward, outputs linked Excel with native formulas. Cash flow reconciliation and balance sheet balancing built-in.

PythonFastAPIXlsxWriterPydantic

E-Commerce Retention & Growth

30-day churn prediction with SHAP explainability. K-Means segments high-value users worth targeting. 0.84 AUC on 484K holdout set. ROI simulator compares retention spend vs revenue saved.

PythonXGBoostSHAPK-Means

Experience

My professional and educational journey

Current Role

Business Intelligence Analyst

Community Hospital

2022 - Present

T-SQLSSRSTableauPower BIExcel

Key Impact

3+ hrssaved per patient

automated clinical chart audits, reducing review time by 75%

VP-levelstrategic reporting

direct to C-suite for operational decision-making

5+production systems

monitoring suicide risk, SDOH, wRVU, and quality metrics

Process ownerquality reporting

designed and implemented clinical quality reporting workflow

Previous:Manufacturing & Operations(2018 - 2022)
Parker HannifinRed Willow Co Sheriff Dept

Education

Dual MBA & M.S. Data Science

Eastern University
Expected 2027

Bachelor of Applied Science

Peru State College
2022

Recent Activity

Continuous learning and shipping.

Latest Commits

Loading commits...

Current Focus

ML Trading Models

Training predictive models for futures trading on CME

Quantitative Research

Backtesting systematic strategies with walk-forward validation

Production ML Pipelines

Real-time inference systems for market analysis

Open Source

Quant tools and data science utilities

Contact

Have a question or want to talk shop? Reach out.

SEND MESSAGE
GitHubLinkedIn

© 2026 Christian Callahan. Built with Next.js & Tailwind.