Case study · 2026 · AI · Web
Twenty matches at once.Built a sports-prediction tool. The math behind every tip is visible, no more guessing in Excel.
BetEdge analyses matches across multiple sports books, builds parlay recommendations on probability math, and surfaces the best odds per outcome in one view. The studio shipped the multi-book ingest, the parlay-building heuristics, and the web + API surfaces.
- Flask
- FastAPI
- SQLite
- Python
Inside the build
Overview
- n-book
- Books cross-shopped
- Parlay
- Probability-built combos
- Explain
- Reason behind every pick
- API
- Programmatic access
Web UI and API: pick a sport, and the system analyses the matches, builds the best parlay, and shows which book has the best odds. It correlates data · it doesn't guess.
What shipped
What it does
- Match and parlay analysis in one place
- Best odds across every book
- A reason behind every suggestion
- Web UI and API both available
The problem
- One person can't analyse 20 matches at once
- Best odds are spread across books
- Random betting doesn't hold up over time
Why it matters
- Data-backed betting decisions
- Best odds in one view
- Parlays built on math, not feel
How it shipped
- 01 · BRIEF
Why random picks lose long-term.
Pinned the value-thesis: positive expected value comes from cross-book odds arbitrage + correlated-bet sizing. Spec'd a tool that ranks parlays by EV, not by 'looks good'.
- 02 · BUILD
Flask front + FastAPI worker + SQLite store.
Flask serves the user surface, a FastAPI worker pulls odds across books on a cron, SQLite persists the historical odds for backtest. Parlay builder runs probability composition with correlation adjustment.
- 03 · SHIP
Web + API · explanations on by default.
Every recommendation comes with a one-line rationale (which odds, which book, why this combo) · the user knows why before placing.
Stack
Ingest
Cross-book odds crawler
Pulls odds from multiple books on a cron · normalises to common markets before comparison.
Parlay
Probability-composed parlays
Builder evaluates correlation between legs · doesn't pretend independent events stay independent.
Best odds
Per-outcome book pick
For each leg, the recommendation surfaces the book with the best odds · easy to follow at the time of placement.
Explainer
One-line rationale per pick
Why this combination, why this book, what the EV looks like · transparent default.
Case study
“We were copying odds across four browser tabs and getting parlays wrong in Excel, embarrassing. BetEdge puts twenty matches on one screen and shows the actual math behind each prediction, including why one is better than another. The only thing left to do is decide whether to place the bet. Our hit rate doubled.”
More work
Next project
ClarixAI