Projects
Builds
Applied machine learning projects developed and evaluated end to end. Each project describes the problem addressed, the approach taken, and how the resulting system was tested. Filter by domain below.
-
ScrubCheck: An NCCI Claim Scrubber Running before Submission
It reviews a claim's procedure codes for NCCI bundling and unit cap edits before submission and explains each flag in clear, plain language.
-
SourceFetch: Grounded Q&A for Billing and Coding Policy
A retrieval augmented assistant that answers billing and coding questions using only the source manuals. It cites the relevant passages and clearly says when the answer is not supported by the available sources.
-
Evaluation and Error Analysis on a Multitask Review Triage Capstone
The evaluation and error analysis workstream for a GWU graduate capstone project focused on a BERT-based triage classifier with five classification heads.
-
Glossary Flashcards: An Image-to-Anki Deck Generator
An updated version of a web application that converts photos of book glossaries into Anki flashcards, remastered using Claude's Vision API.
-
ClosureLabels: Measuring Municipal Service Resolution
An assessment of whether closed municipal service requests remain resolved, using two years of 311 data from a single city.
-
CarbonQueue: Carbon-Aware Batch Job Scheduling System
A queue that schedules deferrable jobs in the cleanest feasible window before their deadline.
-
Free-Tier Benchmark: Assessment Framework for Free LLMs
A benchmark assessing the quality of output from three free-tier LLMs (Perplexity, ChatGPT, and Gemini) across three notebooks and 26 hand annotated cells.
-
RoadTrace: Video-Based Driving Behavior Assessment
A local pipeline for analyzing dashcam footage and generating scored driving-safety reports.
Not all work is public. For questions about a project, get in touch.