How the models work

DataBaller's portfolio of performance models, and the decision metrics they produce, is the intellectual core of the product. Five models — three about a player, two about a team — computed against league data every night, each stored with a record of exactly how its number was made.

Models here improve often, and each league's model versions on its own schedule — the NBA's Performance Shift and the NFL's are siblings trained for their own leagues, not one model wearing two uniforms. This page describes the portfolio as a whole; each model has a page of its own, and every answer in the product names the exact model version behind its numbers, so a figure can always be traced to the method that produced it.

The portfolio at a glance

Player models — two describe, one predicts. Performance Shift and Sustainability Score read a player's game as it is: the role and the production. Scoring Shift is the forward view — it prices what those kinds of evidence say about scoring next.

The question	The model	What it does
Has their game changed?	Performance Shift	Describes
Is their production real?	Sustainability Score	Describes
Where does their scoring go next?	Scoring Shift	Predicts

Team models — both descriptive. Power Rating describes today's strength — in the NBA, of the lineup expected to play; in MLB and the NFL, of the season so far. Ask about a matchup and the forecast is computed on the spot from the two teams' stored ratings.

The question	The model	What it does
How strong is this team?	Power Rating	Describes
Is their record real?	Team Sustainability	Describes

Which version of each model is live in each league, which are on trial, and every test that decided them are on the Decision metrics page, updated every hour. Baseball has no Performance Shift and football no quarterback forecast: both were built and tested, and both failed, so neither ships.

DataBaller's Performance Shift: Has their game changed?

Performance Shift watches a player's job, not their points: minutes, touches and how often the offense runs through them, against the way they were used over the two years before. A high number means the role genuinely moved. Read it as a flag, never a forecast.

How Performance Shift works, and how it has been tested →

DataBaller's Sustainability Score: Is their production real?

Sustainability Score tells production a player is earning from production on loan. Accuracy never settles within a season, so when a player's recent accuracy sits far above their own long-run level, most of that gap is luck, and borrowed points get paid back. Basketball reads shooting, baseball balls in play, football yards per touch.

How Sustainability works, and how it has been tested →

DataBaller's Scoring Shift: Where does their scoring go next?

Scoring Shift is the portfolio's one predictive model: a signed forecast of a player's production over the rest of the season, in points per game, production per hundred plate appearances, or scrimmage yards per game. It is a lean, never a promise, and it is scored in public on its Receipts page.

How Scoring Shift works, and how it has been tested →

DataBaller's Power Rating: How strong is this team?

Power Rating puts a team on the scoreboard's own scale: the margin it would win or lose by against an average opponent on neutral ground. Baseball and football blend the record with the scoring margins; basketball sums the players expected to play. Ask about a matchup and the forecast is computed on the spot from the two ratings.

How Power Rating works, and how it has been tested →

DataBaller's Team Sustainability: Is their record real?

Team Sustainability holds a team's record up against its own scoring margins and measures the gap in wins. Teams far ahead of their margins fall back and teams far behind recover, in every season of every sport we tested.

How Team Sustainability works, and how it has been tested →

The confidence beside every number

Every metric row carries a confidence score that grades the number itself, not the player or the team. It says how much data sits under this particular reading, and it names its own weakness: a short recent stretch, a thin history, or a hole in the underlying data. Rankings only use readings the models are sure of, and when an answer hedges, the hedge names which of those reasons applies.

Tested before they ship

Four things are true of every model above, and each one is checkable rather than promised.

• Computed, never repeated. Every metric is derived first-hand from league data. Nothing here summarizes what analysts and podcasts already concluded.
• Tested against a standard written down first. Every claim was written down before it was tested, then tested against seasons the models had never seen.
• The failures are published. Baseball has no role-change model because its test failed. The scoring forecast failed twice on the way to the version that shipped. The team models shipped with the conventional luck adjustments cut, because the conventional wisdom lost to the data. Marking an NFL team down when the injury report rules out its starting quarterback sounds obvious, and it failed its test too, so the football rating doesn't do it. A model that fails its test is withdrawn, not argued with.
• Every number is reproducible. A stored metric remembers the exact version of the method that produced it, forever — so an answer can always say where a figure came from, even years later.

And the testing never finishes. A model enters the portfolio only with a passed test; it changes only by version, so old numbers keep their meaning; and every claim is scheduled for a fresh test against next season's games, which do not exist yet and cannot be studied in advance. A claim that fails that test is withdrawn too — the football rating, resting on the thinnest margin of the three sports, is first in line for that judgment.

The studies behind the models

The tests that shaped the portfolio are written up one question at a time, with the numbers, the seasons and what each result does and does not license:

• Receipts. Every game's forecast, saved before the start and scored against the closing line once it is final, updated every hour, with the versions on trial beside the live one.
• The Power Rating's first test against the betting line. Six seasons of closing lines in three sports, the four lessons that shape the rating now, and why a gap between the rating and the line is a question rather than an edge.
• What a missing star costs a team. Where the market's edge over a team rating concentrates, and what knowing the lineup is worth.
• Keeping the core together. Roster continuity carries nothing into a new season; the roster's measured impact does.
• Do touchdowns regress?. Touchdown rate is one of the noisiest numbers in football and still persists relative to a player's own history.
• Record against run differential. In MLB the record outpredicted raw run differential, and only a component run estimate restored the signal.
• One-run records and team BABIP. Two classic luck labels persisted, so Team Sustainability reads neither.

These models are decision support. They order the field, size the forces, and state their own limits. Where the data cannot settle a question, DataBaller says so. It won't make the pick.