Edges are the gap between the model's probability and the de-vigged market probability. Higher edge = more potential value. ⚠ = low data confidence.
Model and market disagree by 18.8pt toward Dallas Davison — but confidence is low and the market may know something the data does not. Lines move for reasons: injuries, weight miss, camp news. Check BKFC weigh-in results before betting.
Pat Casey is 10 years older. In bare knuckle, hand durability and cut vulnerability decline fast past 35 — this is a meaningful physical gap.
Model and market disagree by 17.5pt toward David Burke — but confidence is low and the market may know something the data does not. Lines move for reasons: injuries, weight miss, camp news. Check BKFC weigh-in results before betting.
David Simpson is 6 years older. In bare knuckle, hand durability and cut vulnerability decline fast past 35 — this is a meaningful physical gap.
David Burke has a 3" reach advantage — extra distance to land clean jabs and stay outside the pocket unless David Simpson can force infighting.
Tray Martin has finished 100% of BKFC wins by KO — elite finish rate. Going to the cards neutralizes this edge.
Model and market disagree by 21.6pt toward Elijah Harris — but confidence is low and the market may know something the data does not. Lines move for reasons: injuries, weight miss, camp news. Check BKFC weigh-in results before betting.
Peter Barrett is 9 years older. In bare knuckle, hand durability and cut vulnerability decline fast past 35 — this is a meaningful physical gap.
Model and market disagree by 17.9pt toward Stash Kuykendall — but confidence is low and the market may know something the data does not. Lines move for reasons: injuries, weight miss, camp news. Check BKFC weigh-in results before betting.
3-year age gap favors the younger fighter. Watch for cardio and hand durability in the later rounds.
Shane Jordan is making their BKFC debut. The gap from gloved boxing/MMA to bare knuckle is real — cuts, hand swelling, and 2-minute rounds all favor Daniel Pettit's experience.
The PropsBot model is a transparent factor-based scoring system — not a black box. For every bout we score the two fighters on ten+ dimensions, combine via weighted sum, and convert to a probability via a logistic function. That model probability is then compared to the de-vigged moneyline from the market to flag potential value.
Per-factor accuracy from our point-in-time backtest (skipped where data is thin):
Each factor's edge strength is its own sub-score — a 1" reach gap barely moves the needle; a 6" gap is meaningful. Missing data drops a factor's weight to zero rather than guessing.
