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

2017 Second Half Totals

Through 2018-01-09
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1ESPN FPI0.724390.5452312.3880-0.5190257.768410297113217181
2Sagarin Ratings0.712200.5452312.6947-1.4106270.960410292118217181
3The Sports Cruncher0.736710.5449712.3946-1.5430259.172395291104206172
4Computer Adjusted Line0.717070.5348012.3451-0.9037254.950410294116146127
5Logistic Regression0.672320.5335314.7053-4.0144360.288354238116183160
6Linear Regression0.697740.5306112.6867-1.6162266.149354247107182161
7TeamRankings.com0.729270.5289712.5868-0.1849262.800410299111210187
8Donchess Inference0.709760.5264512.6322-1.1064266.548410291119209188
9Sagarin Golden Mean0.717070.5252512.6774-1.3062273.931410294116208188
10Line (updated)0.719510.5251012.3256-0.9183254.153410295115136123
11Edward Kambour0.717820.5204112.9710-1.5862279.370404290114204188
12Massey Ratings0.717070.5201013.3674-1.9242294.345410294116207191
13Dave Congrove0.736590.5175913.1975-0.7139290.355410302108206192
14Sagarin Points0.714630.5175912.6382-1.4283268.495410293117206192
15Ashby AccuRatings0.746340.5174312.5779-0.5778267.351410306104193180
16ComPughter Ratings0.713580.5153113.1438-1.1907284.725405289116202190
17ThePowerRank.com0.709050.5140712.9606-0.7894280.111409290119201190
18Super List0.673170.5125615.0759-0.5391367.594410276134204194
19Born Power Index0.697560.5125613.1452-0.8674283.063410286124204194
20System Median0.714630.5102612.6288-0.8569267.110410293117199191
21Line (opening)0.682930.5094912.4500-0.5695259.817410280130161155
22Atomic Football0.719510.5092312.5707-1.4732265.204410295115193186
23Moore Power Ratings0.692680.5088213.2328-0.9382284.147410284126202195
24FEI Projections0.712500.5066713.41670.0250281.45824017169114111
25Catherwood Ratings0.707320.5052913.2049-0.1561279.941410290120191187
26PerformanZ Ratings0.697560.5050313.6532-0.6442299.843410286124201197
27System Average0.717070.5037812.6392-0.8331267.531410294116200197
28Sagarin Recent0.692680.5037813.4019-1.3580295.566410284126200197
29Dokter Entropy0.712200.5037812.4507-0.5109259.443410292118200197
30Bihl System0.710070.5012713.0763-0.2371278.671407289118198197
31Payne Power Ratings0.707320.5012613.4041-1.8145298.731410290120199198
32Massey Consensus0.643900.5000015.5219-0.2312377.476410264146199199
33Cleanup Hitter0.682930.4987114.0975-0.9632323.318410280130194195
34Stephen Kerns0.698020.4987113.3203-0.6217296.666404282122194195
35Pi-Rate Ratings0.709760.4949712.7849-0.6390277.887410291119197201
36Liam Bressler0.692110.4946212.96970.9657275.987393272121184188
37Stat Fox0.717070.4934413.08300.2295278.833410294116188193
38Keeper0.719510.4924613.2243-0.6696286.294410295115196202
39Billingsley0.697560.4911813.7370-1.0531310.605410286124195202
40DP Dwiggins0.697560.4909113.4146-0.9854294.880410286124189196
41NutShell Sports0.675610.4884314.2850-1.1142337.597410277133190199
42Daniel Curry Index0.700000.4874413.6126-0.4114302.540410287123194204
43PI-Rate Bias0.707320.4872412.7852-0.6294276.406410290120191201
44Least Squares w/ HFA0.658190.4868815.4876-1.0991389.845354233121167176
45Laz Index0.704880.4849212.9363-0.8797275.255410289121193205
46Dunkel Index0.714630.4849214.0968-0.6514318.037410293117193205
47Brent Craig0.721480.4844312.8622-0.5273268.20029821583140149
48Marsee0.716380.4843813.40341.0611288.716409293116186198
49Pi-Ratings Mean0.726830.4833812.7116-0.7300274.677410298112189202
50Lee Burdorf0.700980.4820513.5422-0.7770298.120408286122188202
51ARGH Power Ratings0.719510.4818713.2305-1.1220286.466410295115186200
52Loudsound.org0.692700.4812813.6952-3.9421306.291397275122180194
53Pigskin Index0.702440.4790613.0585-1.1021280.687410288122183199
54Howell0.687800.4766813.4353-1.3718300.880410282128184202
55Roundtable0.711490.4753213.3667-1.0782294.024409291118183202
56Laffaye RWP0.704880.4748713.6755-1.0801306.258410289121189209
57Beck Elo0.685370.4748713.7188-0.7647303.604410281129189209
58Billingsley+0.704880.4698513.7098-0.8356309.560410289121187211
59Talisman Red0.707810.4635413.4187-1.6887294.434397281116178206
60Brent Craig 20.700000.4622614.86161.4155334.47911077334957
61Line (Midweek)0.7024412.4024-0.7756256.603410288122
* 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