Is accuracy betting advice?

No. The page reports historical model performance only; football outcomes remain uncertain.

Public data

AI Football Prediction Quality Report

Name: Football Predictor football prediction dataset
Creator: Football Predictor
License: https://football.edccc.cn/en/about

Public tracking for evaluated prediction samples, hit rate, league cohorts, and model version performance.

Samples

828

Hits

408

Accuracy

49.3%

Public picks

49.4%

League

League	Samples	Accuracy	Draw bias
西甲	160	53.1%	-7.5%
意甲	148	49.3%	-5.4%
英超	136	42.6%	-10.3%
德甲	107	43.9%	-15.9%
法甲	105	41%	-10.5%
世界杯	104	62.5%	-8.7%
欧冠	68	54.4%	-10.3%

Model version

Model version	Samples	Hits	Accuracy
selective-v3	722	351	48.6%
legacy	99	52	52.5%
draw-calibrated-v2	7	5	71.4%

Confidence cohort

Confidence cohort	Samples	Hits	Accuracy
1-4	18	10	55.6%
5-7	753	360	47.8%
8-10	57	38	66.7%

Pick policy

Pick policy	Samples	Hits	Accuracy
Main pick	1	0	0%
Solid lean	250	124	49.6%
Watch list	44	18	40.9%
Avoid / thin data	533	266	49.9%

Prediction type

Prediction type	Samples	Hits	Accuracy
HOME WIN	466	261	56%
DRAW	111	30	27%
AWAY WIN	251	117	46.6%

Data grade

Data grade	Samples	Hits	Accuracy
high	47	17	36.2%
medium	340	159	46.8%
low	342	180	52.6%
unknown	99	52	52.5%

Odds signal

Odds signal	Samples	Hits	Accuracy
With odds	162	88	54.3%
No odds	567	268	47.3%
Unknown odds	99	52	52.5%

Probability margin

Probability margin	Samples	Hits	Accuracy
0-4pp	201	76	37.8%
5-9pp	151	69	45.7%
10pp+	476	263	55.3%

Quality notes

英超平局预测偏少，建议提高低比分/实力接近场景的平局下限。

DRAW 类型命中率偏低，建议检查该结果类型的概率校准。

Methodology

This report only counts latest-round AI predictions for fixtures that have finished and been verified. Accuracy is not betting advice and does not guarantee future outcomes.

Public Dataset and Methodology

Football Predictor publishes public prediction quality samples, field definitions, methodology notes, and responsible-use documentation for review and citation.

View public GitHub repository