Week 15 · December 12 · 11 weeks ahead

College football predictions, week 15

An early look at week 15, from how each team has played so far against the opponents it has faced, adjusted for luck, and where it stood last season. This far ahead fewer games are in, so the curves are wider. On past seasons, forecasts made 11 weeks ahead picked 70.9% of winners, against 74.4% for forecasts made the week before. These update every day: this week’s predictions.

Why the curves are so wide: luck. Even with both teams’ strength known exactly, one game’s bounces, kicks, calls and sequencing move the final margin by about ±13.4 points (one standard deviation, measured from every play). These forecasts carry ±17.1, so about 62% of the width is that luck; the rest is what nobody knows yet about the teams. That is why a 7-point favorite still loses about 3 times in 10.

Game	Our pick	Win chance	Our spread
Navy at Army (neutral site)	Army	68%	−7.9

Navy vs Army

Sat, Dec 12, 3:00 pm ET · neutral site

Army by 7.9 · 68% to win

Ours: Army by 7.9 Navy win 32% Army win 68% 5649423528211470714212835424956 ← Navy win by Army win by → P50 P90 P95

Show as a table

Outcome	Chance
Navy win	32.1%
Army win	67.9%
Middle 50%: Navy by 3 to Army by 20	50%
Middle 90%: Navy by 21 to Army by 35	90%
Middle 95%: Navy by 26 to Army by 42	95%
Exactly Army by 3	6.3%
Exactly Navy by 3	5.3%
Exactly Army by 7	5.3%
Exactly Army by 14	3.9%
Exactly Navy by 7	3.6%

P50: Half of games like this end between Navy by 3 and Army by 20.
P90: 9 in 10 between Navy by 21 and Army by 35.
P95: 19 in 20 between Navy by 26 and Army by 42.

Navy vs Army prediction: the full preview →

Where the forecast comes from
This season, against its opponents	Army	+5.7
Last season	Army	+1.9
Home field	Army	+0.2

How good the forecasts are · Methodology