Last week, we introduced an application for our new method of predicting survival curves, which helps describe how often a quarterback faces pressure after holding on to the ball for a certain time after the snap.
Going into each game, a machine-learning model incorporates a lot of features in order to come up with a prediction:
- The survival curve of the offensive line in previous games (or from last year)
- The survival curve of the defensive line in previous games (or from last year)
- The PFF pass-rush grades of the five offensive linemen
- The PFF pass-rush grades of the pass-rushers, and where they are projected to line up
- How the blend of individual grades and team-level survival curves from the past are weighted toward predicting the cervical curve depends on continuity and how far in the past the information lies. Less continuity means the individual grades are weighted more heavily.
- Schematic factors such as how often the defense is projected to blitz and how often the offense is projected to use play action, designed rollouts or six-plus-man protections.
[Editor's Note: PFF's advanced statistics and player grades are powered by AWS machine learning capabilities.]
Subscribe to
Each week, we will use our projections to highlight the biggest mismatches in the trenches. We will also identify an interesting matchup to watch.
Our model started with mixed results last week, as we expected the Indianapolis Colts' offensive line to dominate against the Jacksonville Jaguars. This was partly accurate, as Philip Rivers got pressured on just 16% of his dropbacks, the third lowest-rate of the week behind Derek Carr and Aaron Rodgers. However, when the Jaguars' pass rush did get to him, it happened pretty fast, as all of the eight pressures Rivers faced came between 2.0 and 2.2 seconds after the snap. Seven of these pressures came from just a four-man rush.
Consequently, 13 offensive lines league-wide were better at protecting their quarterback up to 2.5 seconds after the snap.
However, we nailed our prediction about the Pittsburgh Steelers' defensive line dominating against the New York Giants. Daniel Jones was under pressure within 2.5 seconds after the snap 24 times (42% of his dropbacks) in Week 1, eight times more than the next closest quarterback.
Here are our projected mismatches of Week 2.
Favoring the defensive line: Cincinnati Bengals OL vs. Cleveland Browns DL