We are back with another positional writeup of draft prospects, this time focusing on the offensive line. We previously dove into the quarterbacks, running backs, wide receivers and tight ends.
Thanks to math and feature engineering, we can use natural language processing to compare prospects to their contemporaries and those from the past before tying in advanced descriptive stats that we have built previously to gauge how well a prospect fits within a certain mold performed in the NFL.
For this analysis, we took prospect write-ups from The Athletic's Dane Brugler, who is one of the best football film analysts out there, over the past eight seasons (including 2022) and used latent semantic analysis (LSA) to derive similarity scores between the text in prospects’ scouting reports.
After building our dataset to span eight seasons, we can create a prospect's score in a number of ways. We decided to use a weighted average of similar players’ WAR (wins above replacement), using the similarity score derived above as the weights. For example, if a player has a 0.60 similarity score with a player who has earned 7.0 WAR since being drafted and a -0.3 similarity score with someone who has earned 4.0 WAR, his overall score would be +3.
Using the analyses above, we can look at 2022 prospects in a couple of ways. First, we can examine player comparisons for notable prospects. Second, we can rank the players in each position group by the score derived above. These scores have correlated well with draft position and future WAR generated at the NFL level, although a more robust analysis using more seasons and data sources is beyond the scope of this article.
Let’s start by looking at the most successful NFL offensive linemen's text comparisons so that we can then see what that means for prospects in the 2022 class.
SUCCESSFUL TEXT ANALYTIC TRAITS
BAD TEXT ANALYTIC TRAITS
PLAYERS EXCEEDING THEIR DRAFT PEDIGREE
TREVOR PENNING, NORTHERN IOWA
Few players have seen their stock rise after the college football season like Penning, as his current 16.5 draft position line points toward him landing in the top half of the first round even though he barely squeezed into the first round of mock drafts in December. The reasons are obvious, as Penning offers a unique blend of size and athleticism that is coveted at the offensive tackle position. His closest comparison in this exercise is Andre Dillard with a 46 similarity score. Other hits in his top-10 comparisons include Jonah Williams, Mekhi Becton and Taylor Decker.
DYLAN PARHAM, MEMPHIS
Parham is the third-ranked guard on PFF’s latest big board, but Brugler thinks he projects best as a center. He is extremely quick off the ball and projects as a better run blocker than pass protector at the NFL level. His closest comparison is Quenton Nelson, who lived up to his high draft position and looks like the prototypical interior offensive lineman at the NFL level. Parham scores over a 50 similarity score to Nelson and has no other players close to that in his comparison list. As a Round 2 or 3 selection, Parham looks like an immediate contributor at the NFL level.
DOHNOVAN WEST, ARIZONA STATE
West is the second-highest ranked center on PFF’s big board but has been vastly overshadowed by Tyler Linderbaum during the draft process. That looks like a mistake based on this study, as West checks in as one of the best prospects according to the text analytics. His three closest comparisons (Nick Gates, Graham Glasgow and Ben Powers) all have a similarity score above 40 and have had immediate success at the NFL level. West also has Shaq Mason, Frank Ragnow and Joe Thuney in his top 10, and only two players among his top 10 produced a negative WAR in their NFL career. West may not receive the same buzz as Linderbaum, but he could be an absolute steal in the third or fourth round of the NFL draft.
© 2024 PFF - all rights reserved.