Fight Research

bkfc-99-sheffield-bonner-vs-franco

Friday, February 12, 2027 In 85 days SHEFFIELD
Model v0.1.0 · 56.1% hit rate 2 bouts Model 12:11 PM ET
← Back to card

Every bout on the card

Main Event · Lightweight Title Fight
#1
Ben Bonner 41 ADV
6-2 · age 35
VS
Rico Franco 59 ADV
11-3 · age 33 · 69" reach
Predictability
39 Marginal
Model
41%
59%
Model and market agree closely.
Low confidence
Tale of the tape · factor breakdown
1522
ELO Rating
1564 ★
W
Recent Form
W-W-W
6-2
BKFC Record
11-3
17%
KO Rate
18%
35
Age
33 ★
2.6y ago
Activity
6mo ago ★
0 cuts
Cut History
0 cuts
64%
Opponent Quality
38%
8 fights
BKFC Experience
14 fights ★
5'10"
Height
5'8"
Main Card · Title Fight
#2
Jimmy Sweeney 60 ADV
30-6 · age 41 · 68" reach
VS
James Lilley 40 ADV
10-3 · age 39 · 71" reach
Predictability
66 Solid
Model
60%
40%
Model and market agree closely.
High confidence
Tale of the tape · factor breakdown
1522
ELO Rating
1499
W
Recent Form
L-W
30-6
BKFC Record
10-3
3%
KO Rate
10%
41
Age
39 ★
68"
Reach
71" ★
4mo ago
Activity
2.6y ago
0 cuts
Cut History
0/1 cuts
38%
Opponent Quality
81% ★
36 fights
BKFC Experience
13 fights
5'9"
Height
5'10" ★

Things to consider

James Lilley has a 3" reach advantage — extra distance to land clean jabs and stay outside the pocket unless Jimmy Sweeney can force infighting.

How we predict — and how accurate we've been

56.1%
Model accuracy
on 189 historical picks
+6.1pp
Edge over 50/50
vs coin-flip baseline
481
Bouts backtested
point-in-time, no leakage

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.

BKFC win rate (Bayesian-smoothed)
18%
Recent form (last 5, decay 0.85ⁱ)
14%
BKFC KO rate / finishing ability
13%
Age curve (steep decline past 35)
12%
Reach advantage
10%
Style matchup (pressure/counter/etc)
8%
MMA-background depth
8%
Activity / ring rust
7%
Cut susceptibility (past DS losses)
6%
Strength of schedule
5%
BKFC experience (fight count)
5%
Height advantage
4%

Per-factor accuracy from our point-in-time backtest (skipped where data is thin):

ELO Rating (n=37)
59.5%
Recent Form (n=156)
56.4%
BKFC Record (n=168)
54.8%
Height (n=133)
52.6%
Age (n=187)
52.4%
Reach (n=168)
50.6%

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.

Be honest with yourself: 56.1% accuracy on toss-up-filtered picks means we're wrong roughly 4 out of every 10 bets we recommend. The model is a decision aid, not a crystal ball. BKFC intangibles (cut depth, weight cut, camp news, injuries) aren't fully captured. Never bet more than you can lose on a pick without confirming with additional research.