24 530
Typy checked after the result.
Period: last 120 days · Glicko-2 and math models (no live signals)AI scoreboard
Intelligent AI scoreboard for sports analytics
The AI scoreboard shows automated mecz analytics, wynik probabilities, live signals and post-result model checks.
First we look at strong wyniki and the rynek's zgodność with the model; exact wynik remains a reference rynek.
Publiczny metric
Typ PropickAI accuracy
Available to everyone. Informational. The model is calibrated to the rynek; this is typ accuracy, not betting profitability.
59.32%
Overall hit-rate on the main wynik.
14 550 hits out of 24 530
Model pewność
Average typ
Actual (hit-rate)
Typy
50–60%
53.0%
58.5%
13 013
60–70%
64.6%
65.5%
4 351
70–80%
74.4%
72.2%
2 290
80%+
84.3%
88.2%
1 272
Calibration: the higher the model pewność on the left, the higher the real hit-rate on the right. This means the model's probabilities mecz reality.
Performance by sport
Hit-rate is the share of wyniki correctly predicted by the model. ROI is the historical return on the model's typ wartościowys (flat 1 unit, over the period). Informational, backtest, not a profit guarantee.
Sport
Typy
Hit-rate
Value typy ROI
Tenis
5 188
65.3%
n/a
Piłka nożna
4 272
47.0%
n/a
Koszykówka
1 168
66.4%
n/a
Hokej
364
56.3%
n/a
Siatkówka
288
64.9%
n/a
A hit-rate above the rynek does not guarantee positive ROI: at low kursy even high accuracy can go negative (e.g. tennis). Profit holds where the model agrees with the rynek (basketball).
Method
Jak działa nasza AI
PropickAI compares sports statistics, kursy, Glicko-2, live signals and the results of completed mecze. The AI scoreboard shows which models give a stable signal, where the wynik prawdopodobieństwo is confirmed by the rynek and how typy pass the post-game check.