Wally Chang
Projects

The work, in long form.

A handful of projects, taken apart — a hardware build, a stretch of machine-learning research, and a run of text-mining and risk coursework. Each writeup is the honest version: what worked, what didn't, and why.

5 deep-dives
Project · Shipped · April 2026

doorpi — a door that knows my face and waits for a peace sign.

Pi Zero + ESP32 + MediaPipe. A face-match unlock with a peace-sign verification step before the relay fires.

Solo build · running 24/7 on doorpihost
HardwareComputer VisionPython
Research · American Express, via Cornell · Feb – May 2024

AmEx — when the classifier was most confident, suspect the label.

A research project with American Express. We used a BERT classifier's own confidence to hunt down the mislabeled tickets hiding in its "ground-truth" training data — and learned exactly where a second, fancier approach broke down.

Master's research · led an eight-person team
MLResearchNLP
Independent research · Cornell INFO 4900 · Fall 2023

Morning newsletters — telling the Times from the Brew was the easy part.

An independent-research project text-mining a year of two morning newsletters, scraped by hand. A classifier could tell which was which at about 89%. Predicting the date a newsletter went out — by topic, by token, by fine-tuned BERT — never worked at all.

Solo · advised by Prof. Matthew Wilkens
NLPText MiningBERT
Coursework · Cornell STSCI 5610 · April 2024

The 2008 crisis — watching a bank's beta stop being diversifiable.

A risk-modeling project replicating Chaudhury (2014): rolling-window CAPM in R for Goldman Sachs and JP Morgan across 2006–2010. JP Morgan's beta climbed from 1.29 to 1.85 through the worst of it — and the real-estate funds we added on a hunch moved even more.

Team of three · R, quantmod
RRisk ModelingCAPM
Coursework · Cornell INFO 6350 · Fall 2023

Oscar screenplays — spotting a winner was easier than naming the decade.

A text-mining project over 359 subtitle files — every Academy Award Best Original Screenplay nominee from 1940 to 2022. We expected the decades to separate cleanly and the winners to blur together. It was the other way around.

With Casey Kaufman · Python, scikit-learn
NLPClusteringClassification