National Football League Computer Ratings


Introduction

This is my rough attempt at a computer rating that can, among other things, come somewhat close to predicting final game scores. The actual computer rating, which describes team performance based on games played to date, is found under the "Rating" column. To determine a hypothetical margin of victory, use the "Points" column (just subtract the teams in question) and add in home field advantage (on the right). Predictions are already calculated for upcoming games, on the right.


Ratings last updated Tuesday 12/12/17, 08:55 AM ET Rank Team W L Rating Points BCS 1 Philadelphia 11 2 3.10 57.69 2 2 Pittsburgh 11 2 2.71 54.03 1 3 New Orleans 9 4 2.65 57.74 5 4 Seattle 8 5 2.37 56.46 6 5 Jacksonville 9 4 2.36 57.34 9 6 Minnesota 10 3 2.30 53.98 3 7 LA Rams 9 4 2.30 57.01 8 8 Baltimore 7 6 2.29 56.73 7 9 New England 10 3 1.99 55.81 10 10 Carolina 9 4 1.92 53.51 4 Rank Team W L Rating Points BCS 11 Green Bay 7 6 0.95 51.73 11 12 Atlanta 8 5 0.61 51.43 12 13 Detroit 7 6 0.55 51.21 13 14 Kansas City 7 6 0.45 52.65 18 15 LA Chargers 7 6 0.33 52.04 17 16 Dallas 7 6 -0.05 50.14 16 17 Miami 6 7 -0.57 46.60 14 18 Buffalo 7 6 -0.63 47.36 19 19 Tennessee 8 5 -0.80 45.78 15 20 Washington 5 8 -0.92 47.48 21 Rank Team W L Rating Points BCS 21 Arizona 6 7 -1.28 44.64 20 22 Denver 4 9 -1.29 46.98 23 23 NY Jets 5 8 -1.36 46.57 22 24 Houston 4 9 -1.43 48.19 26 25 Chicago 4 9 -1.47 46.26 24 26 Oakland 6 7 -1.58 46.34 25 27 Tampa Bay 4 9 -2.05 46.06 30 28 San Francisco 3 10 -2.08 45.19 27 29 Cincinnati 5 8 -2.15 44.96 28 30 Indianapolis 3 10 -2.95 41.46 29 31 NY Giants 2 11 -3.09 42.95 31 32 Cleveland 0 13 -3.17 43.71 32
(The "BCS style" ranking is one based entirely on wins and losses, similar to what is used in college football.)

 

PREDICTIONS FOR UPCOMING GAMES Date Away Team Home Team Total Prediction ----------- -------------------- -------------------- ----- -------------- 14-Dec-2017 Denver Indianapolis 39.8 AWAY by -3.84 16-Dec-2017 Chicago Detroit 48.5 HOME by 6.63 16-Dec-2017 LA Chargers Kansas City 35.7 HOME by 2.28 17-Dec-2017 Miami Buffalo 39.1 HOME by 2.44 17-Dec-2017 Green Bay Carolina 50.5 HOME by 3.46 17-Dec-2017 Baltimore Cleveland 34.1 AWAY by -11.34 17-Dec-2017 Houston Jacksonville 40.0 HOME by 10.83 17-Dec-2017 Cincinnati Minnesota 31.7 HOME by 10.71 17-Dec-2017 NY Jets New Orleans 44.9 HOME by 12.85 17-Dec-2017 Philadelphia NY Giants 43.2 AWAY by -13.06 17-Dec-2017 Arizona Washington 39.5 HOME by 4.52 17-Dec-2017 LA Rams Seattle 55.8 HOME by 1.13 17-Dec-2017 New England Pittsburgh 51.6 AWAY by -0.10 17-Dec-2017 Tennessee San Francisco 38.8 HOME by 1.09 17-Dec-2017 Dallas Oakland 43.6 AWAY by -2.11 18-Dec-2017 Atlanta Tampa Bay 27.6 AWAY by -3.70 23-Dec-2017 Indianapolis Baltimore 37.9 HOME by 16.95 23-Dec-2017 Minnesota Green Bay 36.9 AWAY by -0.57 24-Dec-2017 Tampa Bay Carolina 51.3 HOME by 9.13 24-Dec-2017 Cleveland Chicago 35.0 HOME by 4.23 24-Dec-2017 Detroit Cincinnati 47.1 AWAY by -4.58 24-Dec-2017 Miami Kansas City 43.8 HOME by 7.73 24-Dec-2017 Buffalo New England 54.1 HOME by 10.13 24-Dec-2017 Atlanta New Orleans 42.3 HOME by 7.99 24-Dec-2017 LA Chargers NY Jets 36.3 AWAY by -3.79 24-Dec-2017 LA Rams Tennessee 58.7 AWAY by -9.55 24-Dec-2017 Denver Washington 47.4 HOME by 2.18 24-Dec-2017 Jacksonville San Francisco 37.8 AWAY by -10.47 24-Dec-2017 NY Giants Arizona 39.7 HOME by 3.37 24-Dec-2017 Seattle Dallas 42.9 AWAY by -4.64 25-Dec-2017 Pittsburgh Houston 49.0 AWAY by -4.16 25-Dec-2017 Oakland Philadelphia 49.2 HOME by 13.03

Current home field advantage is: 1.68 MAE for games to date: 9.52 These ratings fit to produce 0.68 of the correct winners. Pct when predicted MOV is above 3.36: 0.72 A favored away team rarely loses when favored by more than -6.05. A favored home team rarely loses when favored by more than 6.97.

Above are some statistics about the ratings model. The MAE is the mean absolute error of the ratings fit to all the games played to date. This number is usually larger than you think it should be, but it's a good measure of how variable (or maybe "predictable") game outcomes can be.

Immediately below that, you can see how this best fit does in retro-predicting (there's a better word I'm sure) just the game winners. My favorite stats are the last two--when the home or away team is favored by the given margin, they only lose 30 percent of the time. This is the kind of information that people in the sports wagering world might find useful.


[an error occurred while processing this directive] shopify stats