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

2021 Season Totals

Through 2021-12-05
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Catherwood Ratings0.770270.5000013.74320.6351276.443148114347070
2Massey Consensus0.733240.4847613.60571.1080282.895731536195350372
3Dokter Entropy0.727770.4632513.09990.4198260.263731532199334387
4Laz Index0.726400.4882113.11010.5061261.188731531200352369
5ARGH Power Ratings0.723670.4971513.4576-0.2770281.199731529202349353
6PI-Rate Bias0.723670.5013913.11410.9762260.345731529202361359
7Donchess Inference0.722300.4675113.27130.1053266.990731528203331377
8Line (Midweek)0.7209312.61490.3687245.402731527204
9Super List0.720930.4944415.32321.3623356.364731527204356364
10Pi-Ratings Mean0.720930.5021113.03300.8680257.333731527204357354
11Line (updated)0.720930.4853412.63680.3044245.906731527204149158
12Line (opening)0.719560.5023312.70040.1382249.200731526205324321
13Keeper0.719390.5202213.37891.1921282.567727523204373344
14Edward Kambour0.718190.4868613.22900.5752263.238731525206352371
15Computer Adjusted Line0.715460.4701512.65800.3516246.081731523208189213
16Payne W/L0.715460.4695314.3937-0.9110321.141731523208339383
17TeamRankings.com0.715460.4909113.02640.6355260.157731523208351364
18System Average0.715460.4833812.92090.4208253.856731523208349373
19Billingsley0.714090.4764513.95620.0539306.275731522209344378
20David Harville0.712720.4577013.09070.1360260.463731521210330391
21PerformanZ Ratings0.711350.4792214.01500.3878307.737731520211346376
22Versus Sports Simulator0.710560.4743413.25350.5166268.502729518211342379
23Roundtable0.710260.5031713.60560.5795293.432497353144238235
24System Median0.709990.4734612.90720.4321252.788731519212339377
25ESPN FPI0.709990.4723012.96261.1034258.292731519212341381
26Brent Craig0.709440.5219513.07230.4671263.758413293120214196
27Howell0.709190.4900313.5322-0.3154283.369729517212344358
28Laffaye RWP0.708770.4969813.88820.0672304.734673477196329333
29Pi-Rate Ratings0.708620.5104613.11770.8955260.862731518213366351
30Linear Regression0.707180.5069613.05210.2023260.289362256106182177
31Sagarin Points0.705880.4612213.29870.1515267.874731516215333389
32Massey Ratings0.705880.4854813.4021-0.1630274.564731516215351372
33Payne Power Ratings0.705880.4661113.6216-0.2945287.186731516215337386
34Moore Power Ratings0.704510.4910113.37530.4821277.694731515216355368
35Daniel Curry Index0.700410.4675013.8819-0.0720297.049731512219338385
36Sagarin Ratings0.700410.4467513.22440.1602264.812731512219323400
37Beck Elo0.700410.4910113.46900.6618284.142731512219355368
38Payne Predict0.699040.4647313.81690.1442299.887731511220336387
39DP Dwiggins0.698760.4978513.92300.1183303.285727508219348351
40Talisman Red0.698090.4955413.2858-0.0636268.243679474205333339
41Sagarin Recent0.697670.4758013.58010.2712292.150731510221344379
42Stat Fox0.697670.4913313.37492.1465272.564731510221340352
43Dave Congrove0.695890.5131813.65400.9330285.481730508222370351
44Pigskin Index0.694940.5059213.14770.8636259.115731508223342334
45Bihl System0.694920.4951213.07070.2171258.562413287126203207
46Born Power Index0.693570.4868613.49761.1577275.804731507224352371
47Stephen Kerns0.693570.5097013.87200.9671301.042731507224368354
48FEI Projections0.692970.5096312.96310.1775254.026583404179291280
49Sagarin Golden Mean0.692200.4661113.50520.2220283.036731506225337386
50Logistic Regression0.687850.4624015.5402-2.4646375.449362249113166193
51Least Squares w/ HFA0.687850.5208915.63910.2504371.884362249113187172
52Dunkel Index0.687600.4969013.47921.1920278.069653449204321325
53Cleanup Hitter0.675790.4724214.34890.7772320.517731494237334373
54Loudsound.org0.654650.4786314.7601-3.2510342.776721472249336366
* 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