Finding the Next Justin Jefferson: Rashod Bateman, Random Forests, and the Power of Checking All the Boxes – The Wrong Read, No. 69
Image Credit: Zach Bolinger/Icon Sportswire. Pictured: Rashod Bateman.

Blair Andrews builds on the random forest model described in the Wrong Read No. 68 by turning it into actionable rules for choosing rookie wide receivers. Last year Blair told you that Justin Jefferson was the only WR prospect to check all the boxes. Today, he provides the most similar receivers from the 2021 class.

The best predictive models have three notable criteria — they’re stable, accurate, and interpretable. Not all kinds of models meet all three criteria. A decision tree is both accurate and interpretable, but small changes in the data can have drastic impacts on the model results, which makes a decision tree inherently unstable.

A linear regression does not suffer from quite the same instability, and it is also interpretable. But because it treats every variable as if its relation to the dependent variable can be expressed in a linear equation, it’s not always the most accurate, at least not for predicting how college prospects will perform in the NFL.

A random forest solves the stability problem of a decision tree by growing hundreds of decision trees using random slices of the data. However, the sheer amount of trees and nodes in a random forest model make it a “black box model” — that is, it’s not easily interpretable.

Making Random Forests Interpretable

However, we can solve that last problem using a technique called rule extraction. The basic idea is this: Each node in a decision tree can be thought of as a simple rule or heuristic. These heuristics prove vital in prospect evaluation. Checking all the boxes is even more important than you might have guessed.

Rule extraction algorithms pull those heuristics out of random forest models based on their frequency. The nodes that appear most frequently are taken to be the most important rules, in other words.

We end up with a short list of the most important rules extracted from those hundreds of trees. Some of them are created by combining two nodes that appear frequently in concert. The table below lists those rules, along with some evaluative statistics explaining how good each heuristic is at telling the hits from the misses. For our purposes, if a player averages at least 12.5 PPR points over his first three seasons (a 200-point season pace), I count that as a hit.

Please subscribe For Full Access to all RotoViz content and tools!

 

What’s included in your subscription??

  • Exclusive Access to RotoViz Study Hall
    • A treasure trove of our most insightful articles that will teach you the metrics that matter, time-tested winning strategies, the approaches that will give you an edge, and teach you how to be an effective fantasy manager.
  • Revolutionary Tools
    • Including the NFL Stat Explorer, Weekly GLSP Projections, NCAA Prospect Box Score Scout, Combine Explorer, Range of Outcomes App, DFS Lineup Optimizer, Best Ball Suite,and many, many, more.
  • Groundbreaking Articles
    • RotoViz is home of the original Zero-RB article and continues to push fantasy gamers forward as the go-to destination for evidence-based analysis and strategic advantages.
  • Weekly Projections
    • Built using RotoViz’s unique GLSP approach.
  • Expert Rankings
  • And a whole lot more…

Blair Andrews

Managing Editor, Author of The Wrong Read, Occasional Fantasy Football League Winner. All opinions are someone else's.

How to Build a Contrarian March Madness Bracket: Win Probabilities, Potential Upsets, and Advanced Strategy for the 2024 NCAA Tournament

NFL free agency may be winding down, but our favorite prospects are getting ready for pro days, and best ball drafts are heating up. Yet I have only one thing on my mind: winning my friends and family March Madness pool. The key to winning, as RotoViz readers will already know, is not simply to pick the teams most likely to advance. It’s to pick…...

Gabe Davis’ Impressive Peripherals Hide Some Concerning Advanced Metrics, But Can He Still Provide the Boost Jacksonville Is Looking For?

The Jaguars were one of the first movers in free agency, signing wide receiver Gabe Davis to a three-year deal worth a maximum of $50 million (with $24 million fully guaranteed). Davis has been one of the premier long-touchdown specialists of the last few years, even as many of his key metrics are routinely underwhelming. Yet after Calvin Ridley signed with the Tennessee Titans, Davis…...

How to Build a Contrarian March Madness Bracket: Win Probabilities, Potential Upsets, and Advanced Strategy for the 2024 NCAA Tournament

NFL free agency may be winding down, but our favorite prospects are getting ready for pro days, and best ball drafts are heating up. Yet I have only one thing on my mind: winning my friends and family March Madness pool. The key to winning, as RotoViz readers will already know, is not simply to pick the teams most likely to advance. It’s to pick…...

Gabe Davis’ Impressive Peripherals Hide Some Concerning Advanced Metrics, But Can He Still Provide the Boost Jacksonville Is Looking For?

The Jaguars were one of the first movers in free agency, signing wide receiver Gabe Davis to a three-year deal worth a maximum of $50 million (with $24 million fully guaranteed). Davis has been one of the premier long-touchdown specialists of the last few years, even as many of his key metrics are routinely underwhelming. Yet after Calvin Ridley signed with the Tennessee Titans, Davis…...

The Blitz

Connect
Support

rotovizmain@gmail.com

Sign-up today for our free Premium Email subscription!

Data provided by

© 2021 RotoViz. All rights Reserved.

Welcome Back to RotoViz...

– IF YOU HAVE ISSUES LOGGING IN PLEASE CONTACT ROTOVIZMAIN@GMAIL.COM

– PLEASE NOTE THAT ROTOVIZ USES WORDPRESS FOR ACCOUNT MANAGEMENT. IF RESETTING YOUR PASSWORD YOU MAY BE FOWARDED TO A WORDPRESS PAGE.