Data scientist, physicist, and fantasy football champion

Week 16 DEF Predictions

IND and NO, two of my streaming picks from last week, weren’t great with 5 and 6 points each. WAS worked out alright (10 points).

Hopefully you’re all in the championship game in your league, too. Yahoo’s pros have been better than me this season, but I’m still trusting and using my models C and F. You should too, unless you’re Kyle. In which case, you’re better off not playing a defense this week. Trust me. The models all agree.

Let’s see who might get us through this week:

 

Model A:

.Model A-1.png


Model A parameters:

The team that’s playing
Who their opponent is
Their predicted score
Their opponent’s predicted score
Whether the team is home or away
Model A Notes:

Uses only data from 2017
Standard points
Did well in 2016, but didn’t stand out

Model C:

.Model C-1.png


Model C parameters:

The team that’s playing
Who their opponent is
Their predicted score
Their opponent’s predicted score
Whether the team is home or away
Model C Notes:

Uses data from 2015-2017
Standard scoring
Did well in 2016, but didn’t stand out

Model F:

.Model F-1.png


Model F parameters:

The team that’s playing
Who their opponent is
Their predicted score
Their opponent’s predicted score
Whether the team is home or away
Model F Notes:

Uses data from 2015-2017
Truscor ignores defense TDs but weights interceptions and fumbles to try to account for it
I really liked this one in 2016. It was marginally better than A and C

Model G:

.Model G-1.png


Model G parameters:

The team that’s playing
Who their opponent is
Their predicted score
Their opponent’s predicted score
Whether the team is home or away
Model G Notes:

Uses data from 2015-2017
Truscor ignores defense TDs but weights interceptions and fumbles to try to account for it
Uses Bayesian statistics (Gibbs sampler) to create a model
Would have done very well in 2016 based on simulation

Model H:

.Model H-1.png


Model H parameters:

The team that’s playing
Who their opponent is
Their predicted score
Their opponent’s predicted score
Whether the team is home or away

Model H Notes:

Uses only data from 2017
Uses TruScor points to reduce the effect of TDs

Model I:

.Model I-1.png


Model I parameters may include:

The team that’s playing
Who their opponent is
Their predicted score
Their opponent’s predicted score
Whether the team is home or away
Model I Notes:

Data from 2015-2017
This model tries to predict all of the components of scoring separately (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.

Week 16 model summary:
 

Conclusions

I’ve got LAC this week, so I’m pretty stoked that it’s up a the top of models C and F this week. Let’s see… who does my opponent have… Chicag - aw shit. Chicago is up there, too. Crap. I was hoping he was going fishing this week. Oh well. I’ll just have to beat him elsewhere.

For those of you who didn’t plan ahead like Kyle and I both did, here are some streaming options for the week:

  • PIT (at HOU): A good defense in a great matchup. Houston has been below average with Tom Savage under center, so this is a good play.
  • WAS (v DEN): WAS did fine against an easy ARI last week, and they get an even easier DEN this week. Fire them up with confidence
  • NYG (at ARI): ARI just coughed up 10 points to the mediocre WAS defense last week. The Giants aren’t great this year, but Stanton will probably toss a pick or two

CAUTION:

  • NE (v BUF): Tyrod Taylor collects sacks but doesn’t throw many interceptions. NE will be able to keep the score low, but I think there are defenses with more upside this week
  • CHI (V CLE): DeShone Kizer called me and said he’s done throwing interceptions and getting sacked. This week it’s going to just be TDs to Josh Gordon. All day. Drop Chicago if you have them. Drop them and play the Jets. (seriously though, don’t do this.)

Good luck this week in your championship round.

Week 16 QB Predictions

Week 16 K Predictions