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.

I wouldn't rely at all on early-season results, which are based almost entirely on last year's games. Wait until 3-4 weeks into the season, at least.


Ratings last updated Monday 02/06/17, 08:25 AM ET

Rank Team                   W  L  T   Rating   Points  BCS
   1 New England           17  2  0     3.98     8.82    1
   2 Atlanta               13  6  0     2.75     7.46    2
   3 Dallas                13  4  0     2.13     4.80    3
   4 Kansas City           12  5  0     1.99     4.62    5
   5 Green Bay             12  7  0     1.75     3.11    4
   6 Seattle               11  6  1     1.60     3.31    7
   7 Pittsburgh            13  6  0     1.51     2.63    6
   8 Oakland               12  5  0     1.33     2.16    8
   9 Philadelphia           7  9  0     1.32     4.43   14
  10 Baltimore              8  8  0     0.85     2.42   15

Rank Team                   W  L  T   Rating   Points  BCS
  11 Washington             8  7  1     0.75     1.50   13
  12 Minnesota              8  8  0     0.69     1.84   16
  13 Houston               10  8  0     0.67    -0.04   10
  14 Tennessee              9  7  0     0.64     0.89   12
  15 NY Giants             11  6  0     0.61    -0.98    9
  16 Denver                 9  7  0     0.52     1.98   19
  17 Indianapolis           8  8  0     0.11     0.52   20
  18 Miami                 10  7  0     0.03    -2.12   11
  19 Tampa Bay              9  7  0     0.02    -0.40   18
  20 Detroit                9  8  0    -0.03    -0.90   17

Rank Team                   W  L  T   Rating   Points  BCS
  21 Carolina               6 10  0    -0.25     0.49   21
  22 Arizona                7  8  1    -0.27     0.72   22
  23 Cincinnati             6  9  1    -0.41     0.82   24
  24 New Orleans            7  9  0    -0.53    -0.24   23
  25 Buffalo                7  9  0    -0.77    -0.76   25
  26 San Diego              5 11  0    -1.52    -1.64   27
  27 Jacksonville           3 13  0    -2.45    -3.85   30
  28 NY Jets                5 11  0    -2.66    -7.14   26
  29 Chicago                3 13  0    -2.99    -6.70   29
  30 Los Angeles            4 12  0    -3.03    -8.24   28
  31 San Francisco          2 14  0    -3.76    -8.84   31
  32 Cleveland              1 15  0    -4.60   -10.65   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
-----------  --------------------  --------------------  -----  --------------


Current home field advantage is:  2.44

MAE for games to date:  8.69

These ratings fit to produce 0.69 of the correct winners.
Pct when predicted MOV is above 4.89:  0.82

A favored away team rarely loses when favored by more than -6.10.

A favored home team rarely loses when favored by more than 5.07.


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.


About the author

I have a Ph.D. in Atmospheric Science from the University of Alabama in Huntsville. I am now a faculty member at Indiana University in Bloomington, teaching courses in the broad areas of weather and climate. Don't hesitate to contact me using this email form if you have questions or non-hateful comments. shopify stats