EdgeGoatLearn
How the model was built, what it gets wrong, and how to read a model probability against a sportsbook price.
EdgeGoat's Humble Beginnings
How a frustrating night on the couch turned into a full-blown sports analytics platform.
6 min read
From Spreadsheet Vibes to 65% Win Rate: How We Built a Prediction Engine
The story of turning crude averages into a 16-stage machine learning pipeline — one painful calibration round at a time.
6 min read
What 16 Rounds of Calibration Taught Us About Sports Prediction
Every assumption we had about what matters in basketball prediction was wrong. Here's what actually works.
6 min read
Teaching a GPU to Watch Basketball: Our ML Pipeline
How we went from statistical projections to LightGBM ensembles, neural networks, and contrastive learning embeddings — and the GPU crashes along the way.
7 min read
One Month, Three Leagues, 354 Commits
A look at the absurd pace of building EdgeGoat — told through commit timestamps, 2 AM debugging sessions, and the messages we left for ourselves.
6 min read
Why Your Sportsbook App Sucks (And What We Did About It)
Every sportsbook app is designed to make placing bets easy and tracking them hard. That's not an accident.
5 min read
The Art of the Long-Legged Lottery Parlay
Why we love degenerate parlays, why the math hates us for it, and how EdgeGoat helps tilt the odds back.
6 min read
We Built a March Madness Bracket Projector in One Night
From "feat: brackets" to simulated tournament outcomes in under three hours. Here's how — and what NCAAB prediction taught us that NBA prediction didn't.
6 min read
Scraping Odds From 5 Sportsbooks Without Getting Banned
The cat-and-mouse game of aggregating betting odds — featuring user agent spoofing, headless browsers, and a Caesars anti-bot system that made us question our life choices.
6 min read
From Hoops Stats to OddsDeity to EdgeGoat: The Name Game
We rebranded twice in a month. Here's why each name died and what the final name says about who we're building for.
5 min read
Building an iOS App as an Afterthought (and Why It Worked)
We shipped a mobile app in a day by making one good architectural decision weeks earlier: sharing everything.
5 min read
The Data We Wish Existed (And How We Make Do)
Building a sports prediction engine means constantly hitting the limits of available data. Here's how we get creative when the data we need doesn't come in a nice API.
7 min read