English Premier League
Computer Ratings

Introduction

This is my first rough attempt at a computer rating that can, among other things, come somewhat close to predicting the margin of victory of a match. 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 "Pts" column. You can the calculation for some upcoming games on the right. Don't forget to add in home "field" advantage, which is listed just below the current predictions on the right.

Early season notes:

- predictions are based on much of last season's results until 5 or 6 matches in
- for newly promoted clubs, I might wait an additional few matches to trust the results


Ratings last updated Sunday 04/02/17, 06:18 PM ET

Rank Team                   W  L  T   Rating   Points  BCS
   1 Chelsea               22  4  3     3.62     1.22    1
   2 Tottenham Hotspur     18  3  8     3.41     1.24    2
   3 Liverpool             17  5  8     2.57     0.93    3
   4 Manchester City       17  5  7     2.36     0.82    4
   5 Manchester United     14  3 11     1.87     0.54    5
   6 Arsenal               15  7  6     1.78     0.75    6
   7 Everton               14  8  8     1.44     0.60    7
   8 West Bromwich Albion  12 10  8     0.23     0.01    8
   9 Southampton            9 12  7    -0.62    -0.15   10
  10 Stoke City             9 12  9    -0.63    -0.30    9

Rank Team                   W  L  T   Rating   Points  BCS
  11 Bournemouth            9 14  7    -1.09    -0.41   12
  12 Leicester City         9 14  6    -1.10    -0.44   11
  13 Crystal Palace         9 16  4    -1.19    -0.35   15
  14 Burnley                9 16  5    -1.25    -0.38   16
  15 West Ham United        9 15  6    -1.27    -0.44   14
  16 Watford                9 13  7    -1.37    -0.55   13
  17 Middlesbrough          4 14 11    -1.77    -0.44   19
  18 Swansea City           8 18  4    -2.13    -0.85   18
  19 Hull City              7 17  6    -2.24    -0.95   17
  20 Sunderland             5 19  5    -2.60    -0.85   20

(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      Home Team             Away Team             Total    Prediction
-----------  --------------------  --------------------  -----  --------------
25-Feb-2017  Southampton           Arsenal                 3.0  AWAY by  -0.49

12-Mar-2017  Southampton           Manchester United       2.0  AWAY by  -0.28

13-Mar-2017  Chelsea               Watford                 3.2  HOME by   2.18

04-Apr-2017  Arsenal               West Ham United         3.7  HOME by   1.60
04-Apr-2017  Burnley               Stoke City              2.3  HOME by   0.32
04-Apr-2017  Hull City             Middlesbrough           1.7  AWAY by  -0.10
04-Apr-2017  Leicester City        Sunderland              2.5  HOME by   0.82
04-Apr-2017  Manchester United     Everton                 2.0  HOME by   0.35
04-Apr-2017  Swansea City          Tottenham Hotspur       3.1  AWAY by  -1.68
04-Apr-2017  Watford               West Bromwich Albion    2.4  AWAY by  -0.15

05-Apr-2017  Chelsea               Manchester City         3.7  HOME by   0.80
05-Apr-2017  Liverpool             Bournemouth             3.9  HOME by   1.74
05-Apr-2017  Southampton           Crystal Palace          2.7  HOME by   0.61

08-Apr-2017  Bournemouth           Chelsea                 2.8  AWAY by  -1.22
08-Apr-2017  Crystal Palace        Arsenal                 3.3  AWAY by  -0.70
08-Apr-2017  Everton               Leicester City          3.0  HOME by   1.45
08-Apr-2017  Manchester City       Hull City               2.6  HOME by   2.18
08-Apr-2017  Middlesbrough         Burnley                 1.8  HOME by   0.35
08-Apr-2017  Stoke City            Liverpool               3.0  AWAY by  -0.81
08-Apr-2017  Sunderland            Manchester United       2.5  AWAY by  -0.98
08-Apr-2017  Tottenham Hotspur     Watford                 2.8  HOME by   2.19
08-Apr-2017  West Bromwich Albion  Southampton             2.9  HOME by   0.57
08-Apr-2017  West Ham United       Swansea City            3.4  HOME by   0.82

15-Apr-2017  Crystal Palace        Leicester City          2.6  HOME by   0.50
15-Apr-2017  Everton               Burnley                 2.6  HOME by   1.39
15-Apr-2017  Manchester United     Chelsea                 1.6  AWAY by  -0.27
15-Apr-2017  Middlesbrough         Arsenal                 2.8  AWAY by  -0.78
15-Apr-2017  Southampton           Manchester City         2.7  AWAY by  -0.56
15-Apr-2017  Stoke City            Hull City               2.4  HOME by   1.06
15-Apr-2017  Sunderland            West Ham United         3.3  AWAY by  -0.00
15-Apr-2017  Tottenham Hotspur     Bournemouth             3.3  HOME by   2.05
15-Apr-2017  Watford               Swansea City            3.4  HOME by   0.71
15-Apr-2017  West Bromwich Albion  Liverpool               3.4  AWAY by  -0.51


Current home field advantage is:  0.41

MAE for games to date:  1.22

These ratings fit to produce 0.59 of the correct winners.
Pct when predicted MOV is above 0.82:  0.75

A favored away team rarely loses when favored by more than -0.72.

A favored home team rarely loses when favored by more than 0.79.


Above are some statistics about the ratings model. Home "field" advantage is shown first. 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 to me 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