Birmingham vs Middlesbrough prediction & probabilities (2026-09-19)

Championship

Birmingham vs Middlesbrough Cards

2026-09-19 · 15:00
Cards45.9%Over 3.5 cards
Best predictionOver 3.5 cards · 45.9%Close to a coin-flip, barely a lean. Calibrated, not a tip.
46%

model probability

ConvictionLean

Expert AI analysis

The headline read is Over 3.5 cards at 45.9%, its strongest read on the Cards market. The total-cards ladder runs from 67.6% for over 2.5 to 14.0% for over 5.5, with over 3.5 the closest line to a coin-flip at 45.9%. Between the two sides, Middlesbrough are the model’s pick to pick up more cards at 39.9%, with a level count at 22.3%. Calibrated against real results, we show the read, not a sure thing.

Cards (bookings)

Over 2.567.6%

Over 3.545.9%

Over 4.527.1%

Over 5.514.0%

Total cards, every line

Line Over Under
2.5 cards 67.6% 32.4%
3.5 cards 45.9% 54.1%
4.5 cards 27.1% 72.9%
5.5 cards 14.0% 86.0%

Who picks up more cards

Birmingham37.7%

Level22.3%

★ ModelMiddlesbrough39.9%

Team card lines

Birmingham over 1.5

51.1%

Birmingham over 2.5

24.6%

Middlesbrough over 1.5

52.7%

Middlesbrough over 2.5

26.1%

Card handicap

Birmingham line Birmingham Middlesbrough
-1.5 19.3% 80.8%
-0.5 37.7% 62.3%
+0.5 60.1% 39.9%
+1.5 79.1% 20.9%

Red card

Any red card8.7%

Birmingham red card5.5%

Middlesbrough red card3.4%

Fouls

Line Over Under
20.5 fouls 57.0% 43.0%
22.5 fouls 41.2% 58.8%
24.5 fouls 27.2% 72.8%

Recent referees

The referees each side has met most this season, with cards per game overall and for that team. We never claim who officiates this match: the appointment is not known before kickoff.

Team Referee Games Cards/g Team cards/g
Middlesbrough R Madley 2 2.0 0.5

This season (2026/27)

2.0Birmingham cards per game
12.7Birmingham fouls per game
1.1Middlesbrough cards per game
9.9Middlesbrough fouls per game

Card markets are softer and less efficiently priced than goals, these are the model total-booking probabilities for Birmingham vs Middlesbrough. The model leans toward Middlesbrough for the most cards.

In-depth analysis

Every figure is the model’s own calibrated read, not advice. Calibration is our edge, not beating the market.

45.9%Over 3.5 cards
8.7%Any red card
39.9%Most cards: Middlesbrough
51.1%Birmingham over 1.5 cards
52.7%Middlesbrough over 1.5 cards
41.2%Over 22.5 fouls

By team, Birmingham over 1.5 cards sits at 51.1% and Middlesbrough at 52.7%. A red card for either side is rated at 8.7% (Birmingham 5.5%, Middlesbrough 3.4%). Middlesbrough’s most frequent referee this season, R Madley, has averaged 2.0 cards a game across 2 of their matches; the appointment for this game is not known before kickoff. This season Birmingham have averaged 2.0 cards a game and Middlesbrough 1.1.

Model lenses

Different analytical lenses our model applies to the same calibrated data, not separate tipsters, and never a tip.

The CalibratorRaw model read: 45.9% on Cards, graded against real out-of-sample results, no odds attached.
The Referee WatcherR Madley, Middlesbrough’s most frequent referee this season, averages 2.0 cards a game. The appointment is not known before kickoff, so this is context, not a call.
The FlashpointAny red card is rated at 8.7%, a low-probability event, but one that reshapes every line when it lands.
The DisciplinarianMiddlesbrough are the pick to collect more cards at 39.9%, bookings follow the side defending under pressure.

FAQ

How many cards in Birmingham vs Middlesbrough?
The model rates over 3.5 total cards at 45.9% for Birmingham vs Middlesbrough.

Will there be a red card in Birmingham vs Middlesbrough?
The model rates a red card for either side at 8.7%.

Which team will pick up more cards in Birmingham vs Middlesbrough?
The model rates Middlesbrough to pick up more cards at 39.9%, with a level count at 22.3%.

How is this probability calculated?
We fit a goals and markets model (Dixon-Coles plus an xG strength model and an ensemble) on real match data, then calibrate the output against out-of-sample results. It is a calibrated model probability, not an odds-derived tip.

Is this a betting tip?
No – these are calibrated model probabilities, graded against real results. We publish our full track record, including the misses, and never claim to beat the closing market.

Cards accuracy

How our Cards calls have actually performed, graded out-of-sample against real results.

61.4%Best Cards call, hit rate
0.0223Calibration error
50,317Matches graded

In 10,168 matches we rated like this one (40–50%), Cards actually happened 48.5% of the time.

Predictions & track record updated 18 Sep 2026. See the full, dated track record →

Our last 10 Cards calls

The model’s most recent graded Cards predictions, out-of-sample. Green means the call hit, red means it missed. The number is the model confidence on each.

✗ 71.5%✗ 62.4%✗ 62.6%✓ 68.8%✓ 60.0%✓ 71.6%✓ 66.2%✓ 61.5%✓ 62.7%✓ 55.1%
7 of 10 recent calls hit.
Betis vs Getafe2026-09-17Over 3.5 71.5%Miss
Malaga vs Villarreal2026-09-17Over 3.5 62.4%Miss
Ath Madrid vs Osasuna2026-09-16Over 3.5 62.6%Miss
La Coruna vs Sevilla2026-09-16Over 3.5 68.8%Hit
Barcelona vs Santander2026-09-16Over 3.5 60.0%Hit

More Championship, Cards

All Cards predictions →

Related

Model probabilities, calibration-graded, not a tip. We publish our track record, including the misses. 18+. For information only, not betting advice. If gambling is a problem, visit BeGambleAware.