Kevin Cole's 2018 NFL Betting Model: Week 2
Along with working extensively on NFL projections this season, I’m also putting the data to use projecting game outcomes and scores. We can, of course, apply these projections against the going betting spreads and over/under totals to see where there might be value.
In addition, this information can provide value in DFS by finding teams who are likely to outperform their point totals implied by the spreads and over/unders.
Methodology
The betting model incorporates roughly seven years of historical data to train the model and it was tested on the 2016-2017 seasons, yielding hit rates of roughly 60%. While the model has shown promising results, it is still a work in progress and needs additional testing to boost out-of-sample performance. The numbers below are best viewed as a tool, not the definitive answers.
The model incorporates multiple rolling periods or opponent-adjusted data for offense and defense, adjustments for pace, and adjustment for quarterbacks. Non-quarterback additions and injuries are not built into the model. If you believe Khalil Mack is worth multiple points per game for the Chicago Bears defense, make adjustments accordingly.
The model also looks at QB and team stats together, which can hold down the numbers for teams like the Green Bay Packers who have an excellent QB returning, yet their trailing numbers reflect poor QB play.
The model does not yet account for weather, which isn’t a big concern this weekend. High winds could be a player in Cleveland, so keep that in mind.
“Spread Pick” highlighted in green means the favorite is projected to beat the spread by at least two points. Those highlighted in green means the underdog is projected to beat the spread by at least two points. “O/U Pick” is green for games predicted to go over by at least three points, red of games predicted to go under by at least three points.
Week 1 Review
Last week, the model went 6-4 on side and total plays based on betting lines on Thursday around 5 p.m. ET, or 9-4 based on lines on Sunday morning .
Week 2 Picks
Updated picks as of Sunday at roughly 9 a.m. ET
This week line movements and updating injury info has taken a few plays off the board, versus last week when a few were added. The model technically has TEN-HOU as an “Over”, but that assumes Mariota is the starting QB. Mariota’s playing time and health is too murky and unlikely to be resolved before kickoff.
Picks as of Thursday at roughly 4 p.m. ET
The model sees many more games going under than over, with the average projected total nearly one point below the average over/under. A few of the same teams show up as plays in Week 2 from Week 1, including the Los Angeles Chargers, Denver Broncos, and Bears. The model also projects the Texans to be on the wrong side of a winning play for the second straight week, believing that the offense won’t perform nearly as well as expectations.
By far, the biggest outlier in the model is a projected spread of Los Angeles Rams -5.8 versus the Arizona Cardinals versus the betting line of -13. The truth likely lies somewhere in between, as the model doesn’t see the Rams offense continuing its torrid efficiency against a defense that ranked in the top five in yards per play last season.
The model also isn’t fully buying the smashing Week 1 results of the New York Jets and Washington Redskins, who are likely improved this season, though not to the degree that betting markets assume.
Project versus implied totals
And a closer look at projected points scored versus implied total. Teams highlighted in green could be good places to look for DFS options, the opposite being true for those highlighted in red.
