The pickThe locked winner and its win probability. A priced game's number is built on the market's no-vig price; the model's own margin and total sit beside the market's below, as context.
locked before kickoff
Win chance
95%North Carolina Tar HeelsStrong✓
No moneyline was priced into this call, so it is the model's own number.
Model marginThe model's own predicted margin beside the market's number. Context for reading the game: the model makes no spread pick.
UNC by 27.7market UNC by 36.5
Model totalThe model's own predicted total points beside the market's number. Context for reading the game: the model makes no over/under pick.
50.0 pointsmarket 55.5
Why the model calls itThe reasons behind the winner call, in plain sentences drawn from this page's numbers.
The model has North Carolina Tar Heels at 95% to win, with the market at UNC by 36.5.
No single matchup area stands out; the call rests on the teams' overall results this season, adjusted for who they played.
Rest: UNC has 7 more days since its last game (UNC 14d, ETSU 7d).
Form: UNC has the better last five games by 36.5 points a game (UNC +4.5, ETSU -32.0).
Home field is with UNC, which supports the pick.
ContextThe model makes it UNC by 27.7 against a market UNC by 36.5: 8.8 points of daylight in ETSU's favour. The model's total is 50.0 against a line of 55.5: 5.5 points below it.The model makes no spread or over/under pick: neither has shown an edge over the market in our backtests.
Matchup context: who has the advantageWhich team has the advantage in each area, and how clearly. Context for reading the game, not model inputs.
Model UNC by 27.7 · market UNC by 36.5
ⓘContext, not inputs. These areas show how the two sides match up so you can read the game. The model's call comes from the teams' overall ratings, the quarterback, rest, home field and weather, not from these tiles.
Passing game
–
—
not priced
Ranks unavailable.
Rushing game
–
—
not priced
Ranks unavailable.
Third down & red zone
–
—
not priced
Ranks unavailable.
Big plays
–
—
not priced
Ranks unavailable.
Pass protection & rush
–
—
not priced
Ranks unavailable.
Ball security
–
—
not priced
Ranks unavailable.
Form (last 5)
UNC
Clear advantage
UNC +4.5 per game over the last five, ETSU −32.0.
Market
UNC
Clear advantage
Consensus has UNC by 36.5; the model says UNC by 27.7.
the market, for comparison
Where the lines sitWhere the market's number and the model's sit among every final margin and total in the league's history; the highlighted bars are the games that landed between the two.
3,154 FBS games since 2023
Marginmarket UNC by 36.5 · model UNC by 27.7
Mkt UNC 36.5
Model UNC 27.7
← ETSU by 28tieUNC by 28 →
9.8% of FBS games land between the two numbers. Most common margins: 3 (9.3%), 7 (7.5%), 10 (4.3%), 14 (4.1%).
Totalmarket 55.5 · model 50.0
Mkt 55.5
Model 50.0
24 pts6096 pts
14.6% of FBS games finish between 55.5 and 50.0. The league’s median total since 2023 is 53.
Sharp read
tap to open+
Where the market maker moved the line since open, and whether other books followed. Tracked, not a pick.
Spread
No sharp side yet
Opened
UNC -35.5
→
Market maker now
UNC -35.75
▲ 0.3 since open
→
Retail now
UNC -35.5
in line
2 moves5 books2 led
Sat, Sep 12, 10:20 AM first sharp move: UNC -35.5 → UNC -36
No books followed within six hours
Retail was still UNC -35.5 at that point
Total
No sharp side yet
Opened
51.5
→
Market maker now
54.8
▲ 0.3 since open
→
Retail now
55
in line
5 moves5 books0 led
Sat, Sep 12, 10:20 AM first sharp move: 54.5 → 55
No books followed within six hours
Retail was still 54.5 at that point
The model alone was backtested walk-forward (each game priced only from what came before it). Since the winner call started following the market, the calibration that counts is the record of locked picks on the results page. Margin and total are context, not picks. Model reads, not personalized advice. For information only, not betting advice. 21+ only. Gambling problem? Call or text 1-800-GAMBLER.
