Forecasting 2019 NFL Rookie WR Success: 3-Year Model

Apr 30, 2019

Don Juan Moore/Getty Images

The 2019 NFL Draft is now in the books, giving us dozens of new offensive players to consider for our fantasy teams. In this article, I will discuss some of the key rookie wide receivers to focus on going into 2019 fantasy drafts.

While our friends over at Dynasty League Football (DLF) have not yet released post-draft rookie ADP, I am guessing that N'Keal Harry will end up as the top-ranked rookie receiver. Even though he was only the second receiver taken in the draft (the first was Marquise Brown), he has substantially better opportunity to contribute right away, with John Paulsen giving his situation an A rating. Furthermore, Harry came into the draft with the highest expectations (far ahead of Brown), and most drafters will put a lot of stock in their pre-draft beliefs.

More Rookie Forecasts: RB | LB

Unfortunately, my forecasts of rookie success also put Harry at the top, so while Harry looks like the top receiving prospect in 2019, he will probably also command the highest price. Below, we will discuss some players that might be available at a discount in rookie drafts.

Forecasting Wide Receiver Success

As in the past two years, I am using a combination of two models. The first is a standard statistical model (built using logistic regression) and the second is a more sophisticated machine learning model. The odds reported below take a weighted average of the individual predictions of the two models, which tends to be more accurate than each model individually.

In past seasons, the model has highlighted undervalued players like Cooper Kupp and Kenny Golladay. Last season, it identified Michael Gallup and TreQuan Smith as values at their original price tags.

Next, we will look at the top rookie values at the wide receiver position for 2019:

For those interested, there is a table at the end that shows the predictions from both models for all players drafted in the first six rounds. (Players drafted in the seventh round are just fighting for a roster spot.) In general, the combined model is more accurate. However, the predictions of the individual models are also interesting to look at.