MathBox Doesn’t Give a **** — Week 10 Fantasy Football Rankings based on Machine Learning
No holds barred takes on Week 10 Studs and Duds, Streamers and Busts, Minuses and Plus — Machine learning projections in PPR and Standard scoring leagues
At Fantasy Outliers, we believe that machine learning combined with human expertise leads to better results than either by itself. While some of these projections may seem odd, outlandish even, most of the time, MathBox has a reason for its decisions — and beat ESPN last year for likely starters.
That said, the machine learning models are focused on relevant players, so projections are less accurate for benchwarmers. Also, situational things come up, which require folks like you and me to adjust some of the models’ projections every week.
Okay, let’s get to it…
If you’re looking for Waivers-a-Week-Ahead, go here.
Quarterback Rankings based on Machine Learning
- Cam Newton makes the top of MathBox’s QB rankings for the third straight week! At 80.5 projected points in the next four weeks, he’s +5 above the next slinger in Drew Brees
- MathBox doesn’t care about tough matchups for Matt Ryan, Tom Brady, or Andrew Luck going against the teams who have given up the 13th, 7th, and 5th fewest fantasy points to QBs this season, rating them at 3rd, 4th, and 5th this week, respectively
- MathBox has been relatively low on Patrick Mahomes for the past couple of weeks (and has been wrong). Even though he’s going against Arizona’s #2 ranked Defense against QBs, who cares, you’re starting him
- Marcus Mariota coming in at QB#8 could be a decent under-the-radar streamer at home this week against the Patriots (MB 18.3, ESPN 14)
- Ryan Fitzpatrick should be higher than where MathBox has him, because it thinks he started the whole game two weeks ago when instead, he came in to relieve Jameis Winston of his duties in the third quarter. Hence, another reason why projections need to be reviewed and adjusted by a human.
Running Back — Rankings in Standard and PPR based on Machine Learning
- Nothing surprising at the top here with Alvin Kamara, Todd Gurley, Melvin Gordon, Christian McCaffrey, Kareem Hunt, and James Conner comprising the top 6
- After that, Kenyan Drake comes in at #7 with 19.4 points (versus ESPN 13) away in Green Bay who has been a medium tier matchup for RBs. Not sure what MathBox is seeing here other than potentially a game plan scenario.
- Giovani Bernard, who’s coming off of an injury to play at home versus the Saints is rated at 13.9 points versus ESPN’s 7. I think he could be a great play in a medium-high scoring game, assuming he’s healthy.
Wide Receiver — Rankings in Standard and PPR based on Machine Learning
- Antonio Brown and Juju Smith-Schuster as the #2 and #3 ranked receivers at home versus the Panthers this week? As our projected 3rd highest scoring game, it’s possible
- MathBox likes the Rams receivers in Robert Woods and Brandin Cooks coming in as #8 and #9 in PPR at home versus the Seahawks 20th toughest matchup this week
- Possible value plays include: Tyler Boyd, Marvin Jones, Sterling Shepherd, Julian Edelman, and Larry Fitzgerald
Tight End — Rankings in Standard and PPR based on Machine Learning
- Travis Kelce at 21.4 points as a best guess. WoW. Best tight end in football right now!
- MathBox is high on Vance McDonald at 11.4 points versus ESPN’s 7. It’s a risk, but could be a filler on a bye week
- Other candidates MathBox likes this week include: Jordan Reed, Jimmy Graham, OJ Howard, Eric Ebron and Evan Engram
Defense/Special Teams Rankings based on Machine Learning
- Not sure I’m buying Kansas City and Arizona at the #1 and #2 defenses this week versus each other
- For some reason MathBox is low on the New York Jets at home this week versus the Bills at 6.6 points versus ESPN’s 10. I would start them.
- Both New York Giants and San Francisco who play each other in one of our lower ranked games this week in terms of total points scored could be worthy streamers
Kicker Rankings based on Machine Learning
- These Kicker ranks speak for themselves. Try to find some sneaky points in your league, if you can. Remember, these are in beta version, so use at your own risk!
To dig into our raw, unadjusted projections for Week 10 through the remainder of the 2018 NFL season, go to our Glorious Google Sheet.
- Can machine learning help improve your fantasy football draft — Comparison of Fantasy Outliers’ yearly models’ 2017 fantasy football draft performance versus ESPN and Expert Consensus Rankings
- How Artificial Intelligence (AI) beat ESPN in Fantasy Football — Summary of results of Fantasy Outliers’ weekly predictive models vs. ESPN during Weeks 6–16 of the 2017 NFL regular season