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