loading quinn...
Data ScienceMarket SystemsNortheastern
I like data. In a not evil way.
Most recently, I showed that company peers found by embedding business descriptions move with a firm more than its GICS sector peers do (0.335 vs 0.275 return correlation). Now building a pipeline that pulls ratings and price targets out of public equity research.
Looking for jobs! coops! internships!·January – June 2027
A collection of personal projects. Designed to grow. Named in an annoyingly arbitrary fashion.
A personal pipeline that finds publicly reachable equity-research documents, extracts ratings and price targets for each ticker, and shows them in a dashboard with alerts. It’s under construction, the code is private, and its output has never been used to place a trade.
I embedded the business descriptions of 499 S&P 500 companies and took each firm’s ten nearest neighbors as its peers. Their daily returns correlate with the firm’s at 0.335 on average, against 0.275 for its GICS sector peers (difference +0.060, 95% CI 0.050 to 0.069, 493 firms).
A rule-based system for trading short-term drift in U.S. small caps that absorb information slowly, scored by a five-signal composite and held for 1–3 days. The backtest looked like a weak but real signal. Per-day tests, one of them pre-registered, showed the composite doesn’t rank stocks, so I closed the project.
A backtest of a mechanical plan that buys the pullback after an extreme intraday run-up in a low-priced US stock. It looked slightly profitable until I found reverse splits missing from the price data. Corrected, it loses 4.5% of position per trade after costs (t = −3.83, 421 trades). The code and data are private.
Reads live Level 2 market depth from a Schwab brokerage stream and paints it as a heatmap, with wall, iceberg and pull detection across several symbols. Two renderers share the same data: matplotlib, and a browser canvas fed over WebSocket. MIT licensed.
Twice a day a scraper reads every Monster listing on Amazon, works out the price per fluid ounce, and flags anything at or under the line. This page reads the result live: current deals, the cheapest price by day, and each pack’s own history.
9 under $0.120/oz·updated
Upload a photo and a 17 MB MobileNetV3, running as ONNX in your tab, says whether it’s a true seal, an eared seal (sea lions and fur seals, who are on the same team whatever their name says), a walrus, or none of the above. Trained on iNaturalist photos; the photo never leaves your device.
Roles, positions, and the frequent grill shift.
Student Government · NEU Oakland
Sep 2025 – Sep 2026leadership
Northeastern University
Dec 2025 – Apr 2026experience
PC Building Club
Sep 2025 – Apr 2026leadership
Seb's Snack Bar
Summers 2025 & 2026experience
U.S. Mission to International Organizations
Jul 2021 – Jul 2024experience
fig.01 — Big QI grew up moving every two or so years, and I've come to find comfort in analyzing capricious environments. Pulling and cleaning data, planning and iterating hypotheses, and designing and polishing tools are engagements which fulfill my desire for understanding the systems which affect me.
Those concepts are what led me to studying data science and business administration at Northeastern, where I get to combine my love for optimization with a very silly dog. #likeahusky
When I'm not studying the floor or trying to break my own backtests, you can find me fulfilling my primordial obligations by lifting heavy items off the floor, playing with my dog, or venting about macro uncertainties.
I respond (eventually). A project in mind, want to hire me (╯˘ -˘ )╯, found a bug on this site, or just want to say hi — my DMs are open.
