new, so I dove into the world of machine learning models. Using machine learning to detail the value of a WR prospect is very useful for
dynasty fantasy football.
Machine learning leverages artificial intelligence to identify patterns (learn) from the data, and build an appropriate model. I took over 60 different variables and 366 receiving prospects between the 2004 and 2016 NFL Drafts, and let the machine do its thing. As with any machine, some human intervention is necessary, and I fine-tuned everything down to a 24-model ensemble built upon different logistic regressions.
Just like before, the model presents the likelihood of a WR hitting 200 or more PPR points in at least one of his first three seasons. Here are the nine different components featured, in order of significance:
- Adjusted Age
- Adjusted Receiving Yards Per Pass Attempt
- ESPN Rank
- ESPN Grade
- Career Yards Per Carry
- Receiving Touchdowns Per Pass Attempt
- Career Punt Return Touchdowns Per Game
- School SRS Rating
- Career Kick Return Touchdowns Per Game
This obviously represents a massive change from the original model, proving once again that machines are smarter than humans. I decided to move over to ESPN grades and ranks instead of NFL Draft Scout for a few reasons:
- NFL DS has undergone a lot of site changes, and it is unclear just who is creating the rankings
- Mel Kiper has been a staple of ESPN’s draft coverage for decades, making the ranks and grades more reliable in testing
- The ESPN inputs are relative to an entire class, whereas NFL DS only provided position ranks
Those changes alone made strong improvements to the model, and it should be noted that the ESPN overall ranks have been very closely tied to actual NFL Draft position.
Having an idea of draft position will always help a model since draft position usually begets a bunch of opportunity at the NFL level.
WR Prospect Model History
Since the model is built on drafts up until 2016, I figured perhaps you’d want to see the results from the last three drafts before seeing the 2020 outputs.
| Player | School | Year | Prob |
|---|
| corey davis | Western Michigan | 2017 | 71.9% |
| d.j. moore | Maryland | 2018 | 56.1% |
| christian kirk | Texas A&M | 2018 | 38.9% |
| n'keal harry | Arizona State | 2019 | 38.0% |
| john ross | Washington | 2017 | 35.8% |
| andy isabella | Massachusetts | 2019 | 32.8% |
| taywan taylor | Western Kentucky | 2017 | 29.1% |
| juju smith-schuster | USC | 2017 | 28.4% |
| d.j. chark | LSU | 2018 | 26.8% |
| jj arcega-whiteside | Stanford | 2019 | 26.4% |
| marquise brown | Oklahoma | 2019 | 26.2% |
| dante pettis | Washington | 2018 | 24.6% |
| deebo samuel | South Carolina | 2019 | 24.5% |
| chris godwin | Penn State | 2017 | 21.8% |
| calvin ridley | Alabama | 2018 | 20.2% |
| carlos henderson | Louisiana Tech | 2017 | 19.4% |
| james washington | Oklahoma State | 2018 | 19.3% |
| curtis samuel | Ohio State | 2017 | 18.1% |
| greg dortch | Wake Forest | 2019 | 16.9% |
| tre'quan smith | Central Florida | 2018 | 16.4% |
| a.j. brown | Mississippi | 2019 | 14.2% |
| zay jones | East Carolina | 2017 | 13.2% |
| isaiah mckenzie | Georgia | 2017 | 13.0% |
| malachi dupre | LSU | 2017 | 11.2% |
| dede westbrook | Oklahoma | 2017 | 10.7% |
| courtland sutton | SMU | 2018 | 9.5% |
| quadree henderson | Pittsburgh | 2018 | 9.4% |
| ryan switzer | North Carolina | 2017 | 8.9% |
| josh malone | Tennessee | 2017 | 8.8% |
| keevan lucas | Tulsa | 2017 | 8.4% |
| mecole hardman | Georgia | 2019 | 7.6% |
| dk metcalf | Mississippi | 2019 | 7.3% |
| jordan lasley | UCLA | 2018 | 6.7% |
| michael gallup | Colorado State | 2018 | 6.7% |
| anthony miller | Memphis | 2018 | 6.7% |
| riley ridley | Georgia | 2019 | 6.5% |
| hakeem butler | Iowa State | 2019 | 6.2% |
| keesean johnson | Fresno State | 2019 | 5.6% |
| keke coutee | Texas Tech | 2018 | 5.2% |
| jerome lane | Akron | 2017 | 5.1% |
| mike williams | Clemson | 2017 | 5.0% |
| shelton gibson | West Virginia | 2017 | 4.8% |
| byron pringle | Kansas State | 2018 | 4.7% |
| penny hart | Georgia State | 2019 | 4.6% |
| isaiah ford | Virginia Tech | 2017 | 4.3% |
| kd cannon | Baylor | 2017 | 4.1% |
| ardarius stewart | Alabama | 2017 | 4.1% |
| fred ross | Mississippi State | 2017 | 4.0% |
| preston williams | Colorado State | 2019 | 3.9% |
| deontay burnett | USC | 2018 | 3.7% |
| allen lazard | Iowa State | 2018 | 3.7% |
| diontae johnson | Toledo | 2019 | 3.5% |
| noah brown | Ohio State | 2017 | 3.5% |
| emanuel hall | Missouri | 2019 | 3.2% |
| anthony ratliff-williams | North Carolina | 2019 | 3.1% |
| zach pascal | Old Dominion | 2017 | 3.0% |
| victor bolden | Oregon State | 2017 | 3.0% |
| parris campbell | Ohio State | 2019 | 3.0% |
| equanimeous st. brown | Notre Dame | 2018 | 2.9% |
| braxton berrios | Miami (FL) | 2018 | 2.7% |
| olabisi johnson | Colorado State | 2019 | 2.3% |
| lil'jordan humphrey | Texas | 2019 | 2.2% |
| rodney adams | South Florida | 2017 | 2.1% |
| jaylen smith | Louisville | 2019 | 2.1% |
| miles boykin | Notre Dame | 2019 | 2.0% |
| deon cain | Clemson | 2018 | 1.9% |
| dillon mitchell | Oregon | 2019 | 1.8% |
| keon hatcher | Arkansas | 2017 | 1.7% |
| artavis scott | Clemson | 2017 | 1.6% |
| auden tate | Florida State | 2018 | 1.6% |
| trent taylor | Louisiana Tech | 2017 | 1.6% |
| travis fulgham | Old Dominion | 2019 | 1.6% |
| kelvin harmon | North Carolina State | 2019 | 1.5% |
| kenny golladay | Northern Illinois | 2017 | 1.5% |
| robert davis | Georgia State | 2017 | 1.4% |
| antoine wesley | Texas Tech | 2019 | 1.4% |
| tyre brady | Marshall | 2019 | 1.4% |
| stacy coley | Miami (FL) | 2017 | 1.4% |
| josh reynolds | Texas A&M | 2017 | 1.3% |
| ray-ray mccloud | Clemson | 2018 | 1.3% |
| daesean hamilton | Penn State | 2018 | 1.3% |
| stanley morgan jr. | Nebraska | 2019 | 1.3% |
| terry mclaurin | Ohio State | 2019 | 1.3% |
| jehu chesson | Michigan | 2017 | 1.2% |
| cam phillips | Virginia Tech | 2018 | 1.2% |
| travin dural | LSU | 2017 | 1.1% |
| trey quinn | SMU | 2018 | 1.1% |
| anthony johnson | Buffalo | 2019 | 1.1% |
| chad hansen | California | 2017 | 1.1% |
| amba etta-tawo | Syracuse | 2017 | 1.1% |
| amara darboh | Michigan | 2017 | 1.1% |
| darius slayton | Auburn | 2019 | 1.0% |
| j'mon moore | Missouri | 2018 | 0.9% |
| davon grayson | East Carolina | 2018 | 0.9% |
| travis rudolph | Florida State | 2017 | 0.9% |
| javon wims | Georgia | 2018 | 0.9% |
| damarkus lodge | Mississippi | 2019 | 0.8% |
| nyqwan murray | Florida State | 2019 | 0.8% |
| deangelo yancey | Purdue | 2017 | 0.7% |
| ryan davis | Auburn | 2019 | 0.7% |
| jeff smith | Boston College | 2019 | 0.7% |
| terry godwin | Georgia | 2019 | 0.6% |
| cody thompson | Toledo | 2019 | 0.6% |
| hunter renfrow | Clemson | 2019 | 0.6% |
| drew morgan | Arkansas | 2017 | 0.6% |
| russell gage | LSU | 2018 | 0.5% |
| marquez valdes-scantling | South Florida | 2018 | 0.5% |
| jalen hurd | Baylor | 2019 | 0.5% |
| jaleel scott | New Mexico State | 2018 | 0.5% |
| jester weah | Pittsburgh | 2018 | 0.5% |
| james quick | Louisville | 2017 | 0.5% |
| gabe marks | Washington State | 2017 | 0.5% |
| quincy adeboyejo | Mississippi | 2017 | 0.5% |
| bug howard | North Carolina | 2017 | 0.5% |
| jakobi meyers | North Carolina State | 2019 | 0.5% |
| michael rector | Stanford | 2017 | 0.5% |
| kermit whitfield | Florida State | 2017 | 0.5% |
| jamal custis | Syracuse | 2019 | 0.4% |
| ricky seals-jones | Texas A&M | 2017 | 0.4% |
| jeff badet | Oklahoma | 2018 | 0.4% |
| mack hollins | North Carolina | 2017 | 0.4% |
| jamari staples | Louisville | 2017 | 0.3% |
| tyron johnson | Oklahoma State | 2019 | 0.3% |
| marcell ateman | Oklahoma State | 2018 | 0.3% |
| damore'ea stringfellow | Mississippi | 2017 | 0.3% |
| johnnie dixon | Ohio State | 2019 | 0.3% |
| dylan cantrell | Texas Tech | 2018 | 0.2% |
It is encouraging to see some hits towards the top of the model, but there are obviously some misses as well. Your biggest takeaway here should be just how difficult it is to hit that 200 point threshold. Only two prospects the last three years have even a 40% chance of success. The model is telling us not to be over-confident, and that is a good thing.
WR Prospect Model 2020 Results
Now that you’ve already seen some results, here are the 2020 model outputs.
| Player | School | Prob |
|---|
| Tee Higgins | Clemson | 53.5% |
| Henry Ruggs III | Alabama | 48.9% |
| CeeDee Lamb | Oklahoma | 48.6% |
| Justin Jefferson | LSU | 46.4% |
| Tyler Johnson | Minnesota | 37.8% |
| Geraud Sanders | Air Force | 31.3% |
| Jerry Jeudy | Alabama | 26.0% |
| KJ Hamler | Penn State | 22.8% |
| Brandon Aiyuk | Arizona State | 19.1% |
| Jalen Reagor | Texas Christian | 16.1% |
| Laviska Shenault Jr. | Colorado | 15.5% |
| Quintez Cephus | Wisconsin | 15.1% |
| Michael Pittman Jr. | USC | 11.5% |
| Donovan Peoples-Jones | Michigan | 10.7% |
| Joe Reed | Virginia | 9.3% |
| Denzel Mims | Baylor | 8.8% |
| Isaiah Hodgins | Oregon State | 7.8% |
| Marquez Callaway | Tennessee | 7.7% |
| Antonio Gandy-Golden | Liberty | 5.7% |
| Kalija Lipscomb | Vanderbilt | 4.8% |
| Gabriel Davis | Central Florida | 4.7% |
| Chase Claypool | Notre Dame | 3.8% |
| Bryan Edwards | South Carolina | 3.7% |
| Devin Duvernay | Texas | 3.4% |
| Binjimen Victor | Ohio State | 2.6% |
| Trishton Jackson | Syracuse | 2.3% |
| Cody White | Michigan State | 2.3% |
| Lynn Bowden Jr. | Kentucky | 2.3% |
| Omar Bayless | Arkansas State | 2.2% |
| K.J. Hill | Ohio State | 2.1% |
| Nick Westbrook | Indiana | 1.6% |
| Jonathan Nance | Arkansas | 1.4% |
| Austin Mack | Ohio State | 1.4% |
| Diondre Overton | Clemson | 1.4% |
| Bailey Gaither | San Jose State | 1.3% |
| Quartney Davis | Texas A&M | 1.2% |
| Collin Johnson | Texas | 1.1% |
| James Proche | SMU | 1.0% |
| Jauan Jennings | Tennessee | 0.8% |
| Van Jefferson | Florida | 0.8% |
| JaMarcus Bradley | Louisiana | 0.7% |
| Seth Dawkins | Louisville | 0.7% |
| LaMichael Pettway | Arkansas | 0.7% |
| Lawrence Cager | Georgia | 0.6% |
| Kendall Hinton | Wake Forest | 0.5% |
| Deshaunte Jones | Iowa State | 0.5% |
| Derrick Dillon | LSU | 0.5% |
| Tyrie Cleveland | Florida | 0.4% |
| Darrell Stewart Jr. | Michigan State | 0.3% |
| Scotty Washington | Wake Forest | 0.3% |
| George Campbell | West Virginia | 0.3% |
| Juwan Johnson | Oregon | 0.3% |
Tee Higgins as the top WR is likely surprising for a lot of people, but it shouldn’t be. Higgins had a fantastic career at Clemson, arguably the best school in the country over the course of his career. He is a proven touchdown scorer, and is just over 21 years old with a prototypical body-type.
Nobody is surprised that the second WR on this list is from Alabama, but they are likely shocked to see that a data-based model has Henry Ruggs over Jerry Jeudy. The pair is honestly a lot closer that many people think in a lot of the peripheral statistics. The major edge for Ruggs comes on the ground. He had a 75 yard rushing touchdown, which really underlines his special athleticism and play-making ability.
The name that likely stands out the most is Geraud Sanders, who comes in ahead of Jerry Jeudy despite being a relative unknown out of Air Force. You can mentally bump him down a good bit. The academy schools are a bit of a glitch in the system, as their offensive approach usually yields some outrageous efficiency. Since 2015, 12 of the top 15 seasons in adjusted receiving yards per pass attempt came from either an academy school or Georgia Tech’s triple-option attack. Sanders isn’t a total zero, his profile looks very impressive, but I would have him closer to a 10% chance of success given his likely Day 3 or undrafted outcome in the NFL Draft.
