Week 1, Bills at Ravens
4th-and-2, 7:43 remaining in 3rd quarter, Up by 3
The Ravens punted on a 4th-and-2 on their 47. It’s close, but the NYT 4th Down Bot would have gone for it.
If you disagree

The coach’s decision to punt is the right call if you think the Ravens’ chances of converting on fourth down are less than 50 percent. But based on my analysis, I’d give the Ravens a 56 percent chance to get a first down here.

Here's the full breakdown of my calculations:

Option Chance of converting
Chance of winning
Before play
After play Change
Go for it4th and 2, own 47 56% 68% 69% +1%
Punt 68% 68% -
Field goal try70 yard kick (est.) <1% 68% 58% –10%
My decision in context

Along with some circuitry to come up with a win probability for every game situation, all you need to figure out what you should do next is an estimate of how likely you are to make a field goal or convert a first down.

My estimates for these are based on the results of thousands of similar plays, but you may think you're smarter than I am. This chart shows you how changing those estimates would change my recommendation.

What to do on 4th-and-2 on own 47
Up by 3 with 7:43 remaining in the 3rd quarter
How important was this call?

If the coach had gone for it instead of punting, I estimate the Ravens’ chances of winning would be about 69 percent instead of 68 percent.

What coaches usually do
Punt 85% of the time
Go for it 15% of the time
Field goal try -
Based on about 1,364 fourth downs in similar situations since 2001.
What happened

Sam Koch punts for 46 yards to Buf7. Sam Koch punts for 46 yards to Buf7.

Where did these numbers come from?

To estimate a team’s chances of winning, I use a mathematical model that accounts for a whole lot of variables — including the difference in score, the time remaining in the game, and the number of timeouts each team has left. On top of that, I have models for the likelihood that a team makes a field goal and the likelihood that it will convert a first down.

By combining all of this information, I can come up with the best decision a team can make, according to math.

If you want even more details about the numbers behind my decisions, my full model is available on GitHub. Help make me better!