Data scientist, physicist, and fantasy football champion

Week 15 QB Predictions

My best QB models are still E, H, I, and D (in that order). If you’re using the same scoring system that we do in my league, Illegal Use of Hands, then your QBs are losing 1 point per sack they take. Going with the expert opinions (in this case, Yahoo) is dangerous since they don’t use this system.

I will be using my models this week because they’re awesome and so am I, but also they’re the only ones out there for my specific situation. Let’s see who my models think I should go with this week:

 

Model A:

.Model A-1.png

Terms:

Player
Score
OppScore
Score*OppScore
Home/Away
Home/Away*Player (Some players have a bit more of a problem playing at home or away. Looking at you, Roethlisberger…)
Data years: 2015 - 2017

Model B:

.Model B-1.png

Terms:

Player
Score
OppScore
Score*OppScore
Home/Away
Home/Away*Player
Opponent
Data years: 2015 - 2017

Model C:

.Model C-1.png

Terms:

Player
Score
OppScore
Data years: 2015 - 2017

Model D:

.Model D-1.png

Terms:

Player
Score
OppScore
Opponent
Data years: 2015 - 2017

Bayesian (Gibbs sampler)

Model E:

.Model E-1.png

Terms:

Player
Score
OppScore
Score*OppScore
Home/Away
Home/Away*Player
Opponent
Data years: 2015 - 2017

Bayesian (Gibbs sampler)

Model F:

.Model F-1.png

Terms:

Player
Score
OppScore
Score*OppScore
Score^2
OppScore^2
Home/Away
day (Thu/Sun/Mon)
Data years: 2015 - 2017

Model details: Partial least squares fit

Model G:

.Model G-1.png

Terms:

Player
Score
OppScore
Score*OppScore
Home/Away
Opp
Data years: 2017 only

Model details: Partial least squares fit

Model H:

.Model H-1.png

Terms:

Player
Score
OppScore
Home/Away
Opp
Data years: 2017 only

Model details: Linear model

Model I:

.Model I-1.png

Terms may include:

Player
Score
OppScore
Score*OppScore
Home/Away
Home/Away*Player
Opponent
Data years: 2015 - 2017

Model details: This model tries to predict all of the components of scoring separately (pass yards, pass TD, rush yards, interceptions, sacks, etc.). Each component comes from a linear model containing only the significant terms (p < 0.05) from the list of possible terms above

Model J:

.Model J-1.png

Terms may include:

Player
Score
OppScore
Score*OppScore
Home/Away
Home/Away*Player
Opponent
Data years: 2016-2017 for most people, 2017 only for Alex Smith and Jared Goff

Model details: This model tries to predict all of the components of scoring separately (pass yards, pass TD, rush yards, interceptions, sacks, etc.). Each component comes from a linear model containing only the significant terms (p < 0.05) from the list of possible terms above. I also modified the data years; 2016 and 2017 for most players, 2017 only for Alex Smith and Jared Goff since there’s been so much improvement since last year.

Weekly model summary
 

Conclusions

[Jimmy Garoppolo is too new to really model well with my 2017-only models, but we have a little data from 2016 that might be worthwhile. He also has a bunch of games where he just played a few snaps, so modeling him is going to be tricky.]

Models E, H, I, and D are my best models. Let’s see if we can find some streamers in that pile:

  • Blake Bortles (v. HOU): It’s a tough call to trust Blake Bortles to your fantasy playoffs, but he’s been pretty good this season. In a pinch, he’s not a bad choice.
  • Case Keenum (v. CIN): Fire him up! He technically counts as a streamer because he’s just under 50% owned.

I can’t write this easily because the dummies in my league have 3 QBs each. We’re a 1 QB league. Yeah, there’s a reason why I’m in the playoffs.

Check out Models E and H. They’re right around as accurate as anything out there, and way more accurate than Yahoo in our scoring system. And if you’re in my league: STOP HOARDING QBs YOU DUMMIES!

Week 15 DEF Results

Week 15 DEF Predictions