NFL Machine Learning Picks: Conference Championship

 Final Say

Divisional playoffs have arrived and we’re down to 4 teams. Each of the games' geeky stat comparison can be found here for the NFC and the AFC Divisional Games.

First let me review last week. The Good: SF narrative with Prescott’s fall was accurate. CIN was money but chickened out bc of the offensive line. Should’ve checked the weather. KC I feel like it was still the right side had Mahomes not been hurt. The Ugly: Giants with one of the worst running offenses against the #1 running offense. We gotta notice this!

On to the conference games. 

San Francisco +2.5

If you wait, we may get it at +3, although the +125 straight up seems like a possibility.

It’s tough betting a “rookie” QB against a team that looked unstoppable last week (recency bias). The #1 running offense with a QB that can scramble. AJ is a huge deep threat that could be unstoppable. Of course, a #1 sack defense that can disrupt this rookie. But here’s why I ended up on the 49ers:

  • Buying the narrative that the defense stops the run and bc Purdy throws mostly short, they won’t get to him as much.

  • All the models are crazily pointing at SF winning by an average of 7!

  • I prefer backing a team that has covered 9 of the last 10 vs a team that has a 9-9 ATS record.

  • Home favorites during the playoffs haven’t done well during the playoffs in the past covering 37% since 2000.

  • SF hasn’t lost since McCaffrey arrived. They have more offensive weapons. Offense wins championships.

The AFC game pick can be found on my Rofkin channel: