Computer Rating System Prediction Results for College Football (NCAA IA)

2017 Season Totals

Through 2018-01-09
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Ashby AccuRatings0.742310.4993112.66400.4310259.612780579201362363
2Atomic Football0.741980.4965612.6431-0.3350257.811779578201361366
3Keeper0.739740.5046013.33530.4100289.443780577203384377
4The Sports Cruncher0.737880.5319712.4591-0.3964255.997763563200391344
5Line (updated)0.735900.5307712.27500.1763246.617780574206276244
6TeamRankings.com0.735900.5145512.61870.8390253.192780574206389367
7Computer Adjusted Line0.734620.5318812.28780.1699246.636780573207292257
8Pi-Ratings Mean0.734620.5026512.76520.5531262.567780573207379375
9ComPughter Ratings0.734460.5079812.9387-0.0584270.568772567205382370
10ThePowerRank.com0.733930.4973313.1130-0.0276276.542778571207372376
11Line (Midweek)0.7320512.31540.2987246.627780571209
12System Average0.732050.4881612.63460.1971258.260780571209371389
13ESPN FPI0.730770.5124812.41950.7077248.996780570210390371
14Dokter Entropy0.729490.5000012.49160.5629253.181780569211380380
15Sagarin Points0.729490.5243112.5081-0.2262253.335780569211399362
16Laz Index0.729490.4783212.9295-0.0183267.210780569211364397
17ARGH Power Ratings0.729140.4993213.2166-0.3630281.017779568211365366
18Edward Kambour0.728220.4920013.1962-0.2558279.715769560209369381
19System Median0.728210.4873212.63970.1919258.399780568212365384
20Brent Craig0.727270.4711913.06090.3614272.355605440165278312
21Dave Congrove0.726920.5124813.5219-0.0885296.489780567213390371
22Born Power Index0.725640.5164312.97390.5393277.497780566214393368
23Massey Ratings0.725640.4901413.3692-0.8905283.711780566214373388
24Sagarin Golden Mean0.724360.5125212.7176-0.1869262.586780565215389370
25Donchess Inference0.723650.4960412.8079-0.2873264.827778563215376382
26Pigskin Index0.723080.4910812.83970.4016266.915780564216358371
27Sagarin Ratings0.721790.5348212.6038-0.2247257.640780563217407354
28PI-Rate Bias0.721790.5039812.80110.6465264.341780563217380374
29Pi-Rate Ratings0.720510.5078912.83030.7428266.536780562218386374
30Stephen Kerns0.720050.5060413.65600.8164305.812768553215377368
31Billingsley+0.719230.4809513.75860.0206307.652780561219366395
32Lee Burdorf0.717780.5046613.39610.3271291.637776557219379372
33DP Dwiggins0.717220.4898513.40360.0360286.578778558220362377
34Catherwood Ratings0.716670.4896813.28081.0987281.307780559221356371
35Line (opening)0.715380.5119212.40510.4526249.827780558222322307
36Stat Fox0.715380.4741813.27441.4002279.755780558222349387
37Payne Power Ratings0.714100.5236813.3639-1.2571289.047780557223398362
38Talisman Red0.713910.4804313.5057-0.7093291.081762544218356385
39Liam Bressler0.712980.5164412.86772.0164266.247763544219377353
40Sagarin Recent0.712820.5092113.1485-0.1220277.826780556224387373
41Dunkel Index0.710600.4693613.98700.7832313.402736523213337381
42Daniel Curry Index0.708600.4881613.57590.8275299.339779552227371389
43Moore Power Ratings0.708230.4986813.20720.1592277.833778551227378380
44FEI Projections0.707820.5087713.4938-0.0617283.28824317271116112
45Billingsley0.707690.4750013.8282-0.2159307.356780552228361399
46Marsee0.704370.4816313.97431.7866315.399778548230354381
47Howell0.703850.4764513.5699-0.6108296.249780549231354389
48Roundtable0.703210.4889313.3062-0.8677290.518529372157243254
49PerformanZ Ratings0.702560.5111713.95990.1603313.924780548232389372
50Bihl System0.701490.5109613.1642-0.4077283.271469329140233223
51Beck Elo0.697440.4835713.76940.1230300.236780544236368393
52Linear Regression0.694680.5317912.7521-1.6586267.431357248109184162
53NutShell Sports0.691030.4779114.63600.2520341.971780539241357390
54Laffaye RWP0.691030.4664914.2882-0.6331324.420780539241355406
55Loudsound.org0.687170.5102914.2592-3.8246328.546764525239372357
56Cleanup Hitter0.683330.4805414.6051-0.0216340.375780533247358387
57Brent Craig 20.682820.4524914.10691.6418303.50222715572100121
58Super List0.670510.4960514.92740.4521355.552780523257377383
59Massey Consensus0.669230.4862015.09570.8758353.202780522258370391
60Logistic Regression0.666670.5346814.6741-4.0584359.438357238119185161
61Least Squares w/ HFA0.655460.4884415.4850-1.1590388.671357234123169177
* This system does not make predictions.  I make predictions for this
  system by translating it to a new scale that allows for making predictions.



Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.

The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.

Mean Error = average[abs(prediction-actual)]

      Bias = agerage(prediction - actual)

      Std. = Standard Deviation of individual game biases