Skip to content

Lead README with coaching tools, models and warehouse work #9

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
tdub29 merged 1 commit into from
Oct 31, 2026
Merged

Lead README with coaching tools, models and warehouse work #9

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 11 additions & 7 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,18 +15,14 @@ and evaluation reports below.

## Highlights

- **Can a public-data model beat Vegas? No, and the test says how close it came.** A model
built only from Retrosheet and MLB StatsAPI was frozen, then scored once on 6,451 games from
2023 to 2025. Its log loss trails the no-vig closing line by 0.0036 per game (0.0018, borderline,
once 12 dates with late-scraped "closing" lines are dropped). Its bets at the opening line moved
toward the close by about 2 probability points, but the return cannot be told apart from zero.
The rules for every verdict were written down before the test data was scored.
[Read the report](research/r/mlb/REPORT.md).
- **Coaches use these tools every week.** USD's staff uses the hitter and pitcher apps, the
transfer-portal board and the per-game PDF reports ([samples](docs/samples/README.md)).
- **One method at two levels.** Stuff+ and whiff models are trained on NCAA TrackMan. The xSLG
and swing-decision models are trained on MLB Statcast and applied to NCAA pitches in the hitter
app ([model index](models/README.md)).
- **A dbt/DuckDB warehouse runs from committed fixtures with no credentials.** It rebuilds the
transform layer as staged, tested models. The SQLite pipeline still runs the operational
workflow ([try it](#try-the-sample-dbt-warehouse)).
- **Designed around a 2FA wall.** The NCAA portal login needs a coach's 2FA code every time, so
about 90 percent of the portal workflow runs from public sources with no login at all
([design](docs/transfer-portal-pipeline.md)).
Expand Down Expand Up @@ -76,6 +72,14 @@ The MLB pipelines build player and team estimates from public play-by-play and g
combine them into game forecasts, and evaluate them across seasons. The simulator also models
how a game unfolds, including the starter's exit and which reliever is likely to enter.

**Can a public-data model beat Vegas? No, and the test says how close it came.** A model
built only from Retrosheet and MLB StatsAPI was frozen, then scored once on 6,451 games from
2023 to 2025. Its log loss trails the no-vig closing line by 0.0036 per game (0.0018, borderline,
once 12 dates with late-scraped "closing" lines are dropped). Its bets at the opening line moved
toward the close by about 2 probability points, but the return cannot be told apart from zero.
The rules for every verdict were written down before the test data was scored.
[Read the report](research/r/mlb/REPORT.md).

| Work | What it provides | Methods and results |
|---|---|---|
| Run expectancy and recency | Rolling hitter, starter, bullpen, and team estimates; decay windows, offseason carry, shrinkage, and recent-form experiments | [Recency study](research/r/mlb/RECENCY-PLAN.md) and [R pipeline](research/r/README.md) |
Expand Down
Loading