Performance
Model track record — settled against real results.
Signal distribution by edge
Signals detected to date. The Prime band (4–10% edge at odds 1.40–3.00) is the only one we suggest and track.
Methodology & definitions
All signals recorded from engine launch to date. Each signal represents one detected value opportunity — a single outcome (home/draw/away or over/under) where our Dixon-Coles model assigned higher probability than the bookmaker's implied odds.
A signal is marked WIN if the recommended outcome occurred at match completion. LOSS if the recommended outcome did not occur. Void/push outcomes (cancelled matches, postponements) are excluded from win-rate and yield calculations entirely.
Total profit ÷ total amount staked, expressed as a percentage. Assumes flat 1-unit stakes on every signal. Yield is the primary measure of long-term profitability; positive yield is rare and meaningful.
The percentage price improvement between the odds at signal detection and the final closing odds: (signal_odds / closing_odds − 1) × 100 (stored internally as the log-ratio ln(signal_odds / closing_odds); the percentage shown is e^clv − 1). Positive CLV means we detected value before the market corrected. Sustained positive CLV is widely considered the strongest proof of model edge — more reliable than short-term win rates due to sample-size effects.
Past performance does not guarantee future results. This data is for informational and model-evaluation purposes only. Not financial advice.
Signal history
Value & Longshot results
For information only. Value and Longshot picks are not counted in the headline win-rate, yield or ROI above — that scoreline reflects Prime signals exclusively. These are shared so you can see how the wider, non-suggested edges are landing.
No value results yet — they'll appear here as picks settle.