Projects

Selected case studies.

Methodology-focused write-ups of work I’ve shipped across a decade-plus in BI — from frontline cost-reduction programs to AI-augmented data engineering. Click any card for the full case study.

Note Most of my current work at Verizon is under NDA. The case studies below are anonymized at the systems-and-stakeholders level — the patterns, methods, and outcomes are real; the proprietary specifics are not named.

AI-augmented ETL pipeline automation

in-progress

Used Claude as a development co-pilot to automate a manual 9-step monthly load — with built-in validation, error detection, and a parallel UAT environment.

9 steps

manual → single command

#claude#node.js#bteq#automation

ML-driven churn & disconnect forecasting

shipped

Replaced manual weekly forecasting with Random Forest churn attribution and XGBoost disconnect prediction — 250+ hours of analyst time reclaimed annually.

250+ hrs/yr

forecasting labor reclaimed

#python#xgboost#random-forest#ml

Partner Channel reporting platform

shipped

Stood up a net-new analytics function from fragmented manual tasks to 12+ automated reports serving 5,000+ partner locations — through a Reduction in Force.

5,000+

partner locations served

#governance#reporting#automation#leadership

OCC cost reduction analytics program

shipped

Outlier detection, cohort journey analysis, and finance modeling that took an unfavorable Q1 OCC program to $28M+ favorable for the year — against a $300M annual spend.

$35.78M

favorable to budget

#python#outlier-detection#finance-modeling

Self-serve analytics infrastructure

shipped

Built a scalable Tableau dashboard automation backend — from 10 dashboards in 2023 to 30+ in 2024, with anomaly detection and zero manual refresh.

30+

dashboards automated

#tableau#python#bteq#automation