Breakout Receiver Model: Week 6

Oct 09, 2024

Kelley L Cox-Imagn Images

Welcome back to the breakout receiver model for Week 6 of the NFL season. The model had its first heater of the season, with 22 total players who had previously been underperforming expectations able to meet or exceed those expectations in Week 5, including five players who topped 20 fantasy points. This means that despite this being a topsy-turvy year in terms of injuries and game outcomes, the same signals that predicted breakouts in previous seasons are almost certainly still strong signals this season.

Each week we use the model to identify players who may be over- or underperforming the value of their opportunity, whether that be due to luck, skill, or a variety of the two. We'll use the model to identify buy-low and sell-high candidates for season-long players. Then we'll analyze the main slate in an attempt to locate players with a higher likelihood of hitting a ceiling performance than the public perceives. Let’s dig into the data for this week.

About the Breakout Receiver Model

The 4for4 data science team, in conjunction with our award-winning projections expert John Paulsen, created the current iteration receiver "buy-low" model in order to use machine learning to identify under-performing wide receivers and tight ends on the verge of a breakout performance. The model utilizes historical data and recent player performance to help determine players who have received opportunity that is typically more valuable than recent production would indicate. This particular model's features include air yards and routes-run data as a means of determining opportunity. It also utilizes a proprietary efficiency metric that looks back at the past 10 weeks of individual player performance, all to better help predict the likelihood of a bounce-back in a player's future production. The model most heavily weights the last three weeks of data.