You scumbag, you maggot, you cheap lousy faggot "Fairytale of New York" - The Pogues

About DeepFij

DeepFij is college basketball, quantified: scores, schedules, box scores, power ratings, and machine-learning game predictions for every Division I program, updated daily through the season.

This site has been a labor of love for 25 years. It has been partially implemented in C, C++, Java, Scala, Ruby, Python, and Node. The datastore has been text files, MySQL, MongoDB, and Postgres. For a while the project existed to me simply as a known problem, with which I could experiment with new technology. That's kind of how it is now, but now the new technology is LLM's. Thanks to their magic it is now in a state suitable for public viewing. Be advised it's not my day job, and is always presented on a best efforts basis. No warranty expressed or implied.

Almost nothing on this site is terribly novel. (Maybe the game chart). `Massey` and `Breadley-Terry` have been 'discovered' independently by a number of people including. The citations I include below are the first or best published reference I know. The pace, efficiency, and all the other modern stats are due to work by Dean Oliver an d Ken Pomeroy. Thjose guys along with Keith Massey are the OGs of team ratings.

Predictions come from a family of models — classical Massey and Bradley-Terry ratings alongside gradient-boosted ML models — and every pre-game prediction is scored against the final result and the closing line, in public, on the model performance page.

Game data is sourced from ESPN's public APIs. DeepFij is an independent analytics project and is not affiliated with ESPN or the NCAA. This is not betting advice.

367 Teams
32,406 Final games
6 Seasons
33 Conferences

Relevant Literature

If you feel these references are incomplete or I fail to give proper credit, please let me know at deepfij@gmail.com.

Team ratings

Pace & efficiency

Machine learning & evaluation

Tempo-adjusted efficiency ratings were popularized in college basketball by Ken Pomeroy (kenpom.com) and Bart Torvik (barttorvik.com), whose public work shaped the conventions this whole genre of analysis follows.