This is an exercise in building a simple blind predictive model based on a team’s historical stats in 4 areas: pass and rush efficiency, and avg EPA for special teams and penalties. The season-long experiment will track how well future games are determined by past statistical performance and compare that record against Vegas betting lines.
All data used originates from Pro Football Reference and nflFastR.
The model continues its strong performance, picking 5 of 6 winners straight up in Wildcard Weekend. It correctly forecasted the Browns to upset the Steelers and so gained a game on Vegas for the season, sitting 2 games back at a 66.4% accuracy rate with only 7 games left.
Against the spread, it went 5 for 6, missing only on Chicago to stay within 10 points against New Orleans. That puts the season's total accuracy at 56.4% ATS.
In the second week of the playoffs, the model likes the Ravens to upset Buffalo giving it a chance to either close to within a game of Vegas or fall to 3 back.
The math also really doesn’t think much of KC giving them the win, but only by 1 point.