Open Access

All predictions, models and accuracy data are currently open so you can verify our results first-hand. No signup, no paywall — full transparency.

Subscription plans & API access launch May 14, 2026.

Signal Analytics

Return analysis across markets, leagues and allocation methods
Early-Stage Data 19d

Our models went live on 2026-03-22 — only 19 days of forward-looking data have been collected so far. Yield and win-rate figures will stabilise as more matches are played and scored. All numbers shown are strictly prospective: only predictions made before kick-off are counted.

Results are accumulating daily. Check back regularly for updated figures.

4/14 Markets where our models demonstrate a sustained edge over bookmaker odds.
Total Signals
176
81 fixtures analysed
Win Rate
38.6%
68 / 176 correct
Weighted average across all markets. Signals on low-probability outcomes (draws, clean sheets) lower this number — what determines profitability is Yield, not Win Rate.
Yield (Equal-Weight)
-11.3%
Positive = net profit per unit risked
Growth (Proportional)
-25.6%
Risk-adjusted allocation
7D 30D 90D All
2026-03-22 to 2026-04-09 (19 days)
Cumulative Yield
Return by Market
Return by League
Top 15 by signal count
Signal Strength Distribution
Model advantage vs. implied probability

Edge = the difference between the model's estimated probability and the market-implied probability (1/odds). Bars show how many signals fall in each edge range; the line shows the win rate for each range. Note: win rate is not expected to increase linearly with edge — high-edge signals often target low-probability outcomes (draws, clean sheets) where the model sees large value relative to the market but the base win rate remains low. When a bucket contains fewer than ~50 signals, the win rate line may fluctuate significantly due to small sample size.

Return by Country
Methodology

A signal is generated when our model identifies an edge of at least 2% between its estimated probability and the market-implied probability. Only predictions created before the match starts are included — no backtesting, no hindsight.

For informational and educational purposes only. Past statistical performance does not guarantee future results. This does not constitute financial advice.

Last updated 3 hours ago