MathBox Tells It Like It Is — 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 for the 2019 NFL season

To view our product line, visit us on our gumroad page. For daily updates, follow us on twitter.

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 for likely starters (also, tied Vegas in predicting game winners).

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.

These models are projecting using DraftKings PPR scoring, which is a little higher on average than ESPN PPR scoring — so keep that in mind when making comparisons between the two

Okay, let’s get to it…

Quarterback Rankings based on Machine Learning

• Josh Allen has an away game against a middle-tier opponent in the Cleveland Browns (18th most points to QBs this year). At 26.5 points and $6,300 DraftKings cost, that’s a low 237.6 dollars / point. We have him at about 61 rushing yards and 0.5 rushing TDs (Betting Tools).

Week 10 Quarterback Ranks

Running Back — Rankings in Standard and PPR based on Machine Learning

• David Johnson has one of the best DraftKings values among running backs this week at 293 cost / point, despite going against the #2 ranked fantasy rush defense away in Tampa Bay.
• MathBox is also high on Tarik Cohen, projecting 15.7 points (ESPN 10) and 10 opportunities, at home against a forgiving Detroit Lions run defense. (Fantasy League)

Week 10 Running Back ranks DraftKings PPR

Week 10 Running Back ranks ESPN Standard

Wide Receiver — Rankings in Standard and PPR based on Machine Learning

• Hello Stefon Diggs. While ESPN has him as a WR2 this week at 14.6 points, MathBox is rating him at 22.1 points with 8.5 targets and a 60–70% chance of scoring at least 1 TD (Betting Tools). Will Adam Theilen be out again this week?
• Sammy Watkins at 18 projected points versus ESPN’s 13.5 has a low DraftKings cost per point among top receivers at 282.6 cost / point (Fantasy League).

Week 10 Wide Receiver ranks DraftKings PPR

Week 10 Wide Receiver ranks ESPN Standard

Tight End — Rankings in Standard and PPR based on Machine Learning

• MathBox is all over George Kittle against Seattles 29th ranked fantasy defense against tight ends. Probably not alone there. Betting Tools is projecting 92.3 receiving yards, 79% chance of 1 or more touchdowns — including a reasonable shot at more than 2 TDs.
• MathBox is high on Jared Cook at 13.6 points versus ESPN’s 8.8. He’s only owned in 65% of leagues, so he may be available. (Fantasy League)

Week 10 Tight End ranks DraftKings PPR

Week 10 Tight End ranks ESPN Standard scoring

Defense/Special Teams Rankings based on Machine Learning

• Defense/Special Teams projections are taking a bye week this week!

Kicker Rankings based on Machine Learning

• In a close match-up this week? Consider someone like Minnesota Vikings’ Kicker Dan Bailey (MathBox 8.9 vs ESPN’s 7.0 points) or someone else near the top of this list who’s available in your league.

Week 10 Kicker ranks

We have products geared towards fantasy leagues, DFS players, and NFL bettors. Check ’em all out on our gumroad profile page.

Performance analysis:

• 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
• We Tied Vegas in Our First Attempt at Predicting NFL Game Winners Using Machine Learning — How Raw, Unedited Machine Learning Models With Information Known Early in the Week Tied Final Vegas Game Winner Projections and the Spread

To stay in touch, please, join us by following us on Twitter (@fantasyoutliers) or subscribing to our weekly newsletter. We’re a small team, so let’s grow together!