Premier League 2026-27

LIVE

20,000 simulated seasonsfrom a model that blends this site's own season data with market odds, replays the real results as they land, and predicts every fixture - then keeps score on itself all season.

poisson-v2-v3 · updated 2026-09-15 · after 40 matches

The title race

Share of simulated seasons each club finishes first.

1Arsenal55%1.5pp

2Manchester City40.8%1.8pp

3Liverpool2.8%2.2pp

4Chelsea1.1%0.7pp

5Brighton & Hove Albion0.2%0.1pp

6Manchester United0.1%0.2pp

The relegation battle20 clubs

Share of simulated seasons each club finishes in the bottom three.

1Coventry City86%10.1pp

2Hull City83.4%2.3pp

3Ipswich Town49.9%15.6pp

4Sunderland34.9%6pp

5Fulham11.8%0.6pp

6Crystal Palace10.7%4.1pp

7Tottenham Hotspur6.8%0.8pp

8Aston Villa3.8%1.7pp

9Nottingham Forest3.5%2.3pp

10Everton2.9%0.1pp

11AFC Bournemouth2.3%0.4pp

12Leeds United2%2.2pp

13Brentford1.2%0.1pp

The next fixtures, called10 fixtures

The next fixtures, called

Win-draw-win probabilities for the upcoming round.

How this is measured

Market odds join each column once the books post them. Every prediction is frozen when first published and graded against the real result below.

Brentford

v Chelsea

Fri 18 Sept

Model 34%/23%/43%

Chelsea

Brighton & Hove Albion

v Arsenal

Sat 19 Sept

Model 16%/22%/61%

Arsenal

Everton

v Ipswich Town

Sat 19 Sept

Model 64%/21%/15%

Everton

Newcastle United

v Hull City

Sat 19 Sept

Model 85%/10%/5%

Newcastle United

Nottingham Forest

v Coventry City

Sat 19 Sept

Model 63%/21%/16%

Nottingham Forest

Tottenham Hotspur

v Aston Villa

Sat 19 Sept

Model 39%/25%/36%

Tottenham Hotspur

AFC Bournemouth

v Liverpool

Sun 20 Sept

Model 25%/22%/53%

Liverpool

Fulham

v Manchester United

Sun 20 Sept

Model 30%/24%/46%

Manchester United

Leeds United

v Crystal Palace

Sun 20 Sept

Model 43%/27%/30%

Leeds United

Manchester City

v Sunderland

Sun 20 Sept

Model 85%/11%/4%

Manchester City

Date	Fixture	Home	Draw	Away	Pick
Fri 18 Sept	Brentford v Chelsea	34%	23%	43%	Chelsea
Sat 19 Sept	Brighton & Hove Albion v Arsenal	16%	22%	61%	Arsenal
Sat 19 Sept	Everton v Ipswich Town	64%	21%	15%	Everton
Sat 19 Sept	Newcastle United v Hull City	85%	10%	5%	Newcastle United
Sat 19 Sept	Nottingham Forest v Coventry City	63%	21%	16%	Nottingham Forest
Sat 19 Sept	Tottenham Hotspur v Aston Villa	39%	25%	36%	Tottenham Hotspur
Sun 20 Sept	AFC Bournemouth v Liverpool	25%	22%	53%	Liverpool
Sun 20 Sept	Fulham v Manchester United	30%	24%	46%	Manchester United
Sun 20 Sept	Leeds United v Crystal Palace	43%	27%	30%	Leeds United
Sun 20 Sept	Manchester City v Sunderland	85%	11%	4%	Manchester City

How the model is doing10 fixtures

Picks

18/40

match calls correct

Model Brier

0.6675

lower is better; 0.667 = guessing

Market Brier

0.654

the benchmark to beat (30 priced)

Leeds United

v Newcastle United

Pick: Newcastle United · Brier 0.722

Leeds United ✕

Manchester United

v Manchester City

Pick: Manchester City · Brier 0.305

Manchester City ✓

Coventry City

v Brighton & Hove Albion

Pick: Brighton & Hove Albion · Brier 0.210

Brighton & Hove Albion ✓

Tottenham Hotspur

v Everton

Pick: Tottenham Hotspur · Brier 0.820

Draw ✕

Sunderland

v Arsenal

Pick: Arsenal · Brier 0.100

Arsenal ✓

Liverpool

v Fulham

Pick: Liverpool · Brier 1.227

Draw ✕

Crystal Palace

v Ipswich Town

Pick: Crystal Palace · Brier 1.111

Ipswich Town ✕

Chelsea

v Hull City

Pick: Chelsea · Brier 1.731

Draw ✕

Aston Villa

v Nottingham Forest

Pick: Aston Villa · Brier 0.874

Nottingham Forest ✕

AFC Bournemouth

v Brentford

Pick: AFC Bournemouth · Brier 0.869

Draw ✕

Date	Fixture	Our pick	Result	Brier
Mon 14 Sept	Leeds United v Newcastle United	Newcastle United ✕	Leeds United	0.722
Sun 13 Sept	Manchester United v Manchester City	Manchester City ✓	Manchester City	0.305
Sun 13 Sept	Coventry City v Brighton & Hove Albion	Brighton & Hove Albion ✓	Brighton & Hove Albion	0.210
Sat 12 Sept	Tottenham Hotspur v Everton	Tottenham Hotspur ✕	Draw	0.820
Sat 12 Sept	Sunderland v Arsenal	Arsenal ✓	Arsenal	0.100
Sat 12 Sept	Liverpool v Fulham	Liverpool ✕	Draw	1.227
Sat 12 Sept	Crystal Palace v Ipswich Town	Crystal Palace ✕	Ipswich Town	1.111
Sat 12 Sept	Chelsea v Hull City	Chelsea ✕	Draw	1.731
Sat 12 Sept	Aston Villa v Nottingham Forest	Aston Villa ✕	Nottingham Forest	0.874
Sat 12 Sept	AFC Bournemouth v Brentford	AFC Bournemouth ✕	Draw	0.869

Every club, every outcome20 clubs

Every club, every outcome

Expected points, finishing range and odds for each landing spot.

How this is measured

The title, the top four (automatic Champions League), the top five/seven (Europe) and the bottom three. “Finish” is the median simulated position with the 5th-95th percentile range.

Sort by

Arsenal

Solid

99.4%

xPts 89.8 (79-100)

Manchester City

Solid

98.7%

xPts 87.6 (77-98)

Liverpool

Lean

71.9%

xPts 72.4 (61-84)

Chelsea

Toss-up

48.3%

xPts 67.2 (55-79)

Brighton & Hove Albion

Unlikely

23%

xPts 60.9 (49-73)

Manchester United

Unlikely

18%

xPts 59.2 (47-71)

Newcastle United

Unlikely

15.5%

xPts 58.4 (46-70)

Brentford

Out

6.8%

xPts 53.9 (42-66)

Leeds United

Out

3.9%

xPts 51.6 (40-63)

AFC Bournemouth

Out

4.1%

xPts 51.3 (39-63)

Everton

Out

2.4%

xPts 49.5 (38-61)

Nottingham Forest

Out

2.6%

xPts 49.5 (38-61)

Show all 20 clubs

Aston Villa

Out

3%

xPts 49.4 (37-62)

Tottenham Hotspur

Out

1.3%

xPts 46.2 (35-58)

Crystal Palace

Out

0.6%

xPts 43.7 (32-56)

Fulham

Out

0.5%

xPts 43.1 (32-55)

Sunderland

Out

<0.1%

xPts 36.0 (26-47)

Ipswich Town

Out

<0.1%

xPts 33.6 (23-44)

Hull City

Out

0%

xPts 26.4 (18-36)

Coventry City

Out

0%

xPts 24.6 (15-35)

Club
ArsenalSolid	89.8(79–100)	1(1-3)	55.0%1.5pp	99.4%0.6pp	99.8%	>99.9%	0%0pp
Manchester CitySolid	87.6(77–98)	2(1-3)	40.8%1.8pp	98.7%1.1pp	99.6%	99.9%	0%0pp
LiverpoolLean	72.4(61–84)	3(2-8)	2.8%2.2pp	71.9%2.4pp	83.4%	94.1%	<0.1%0pp
ChelseaToss-up	67.2(55–79)	5(2-11)	1.1%0.7pp	48.3%3.8pp	64.4%	82.9%	<0.1%0pp
Brighton & Hove AlbionUnlikely	60.9(49–73)	6(3-13)	0.2%0.1pp	23%10.5pp	38%	62.4%	0.1%0.4pp
Manchester UnitedUnlikely	59.2(47–71)	7(3-14)	0.1%0.2pp	18%1.6pp	31.1%	55.3%	0.3%0.1pp
Newcastle UnitedUnlikely	58.4(46–70)	7(3-14)	0.0%0.2pp	15.5%6.6pp	27.5%	51.1%	0.4%0.2pp
BrentfordOut	53.9(42–66)	9(4-16)	0.0%0pp	6.8%0.7pp	14.2%	32.8%	1.2%0.1pp
Leeds UnitedOut	51.6(40–63)	10(5-16)	0.0%0pp	3.9%2.3pp	8.6%	22.9%	2%2.2pp
AFC BournemouthOut	51.3(39–63)	10(5-17)	0.0%0pp	4.1%0.3pp	8.9%	23.3%	2.3%0.4pp
EvertonOut	49.5(38–61)	11(5-17)	0.0%0pp	2.4%0.1pp	5.5%	16.8%	2.9%0.1pp
Nottingham ForestOut	49.5(38–61)	11(5-17)	0.0%0pp	2.6%1.2pp	6%	17.2%	3.5%2.3pp
Aston VillaOut	49.4(37–62)	11(5-17)	0.0%0pp	3%1.3pp	6.5%	18%	3.8%1.7pp
Tottenham HotspurOut	46.2(35–58)	13(6-18)	0.0%0pp	1.3%0pp	3%	9.9%	6.8%0.8pp
Crystal PalaceOut	43.7(32–56)	14(7-18)	0.0%0pp	0.6%0.4pp	1.7%	6.3%	10.7%4.1pp
FulhamOut	43.1(32–55)	14(7-18)	0.0%0pp	0.5%0pp	1.6%	5.9%	11.8%0.6pp
SunderlandOut	36.0(26–47)	17(11-20)	0.0%0pp	<0.1%0pp	0.1%	0.7%	34.9%6pp
Ipswich TownOut	33.6(23–44)	17(12-20)	0.0%0pp	<0.1%0pp	0.1%	0.5%	49.9%15.6pp
Hull CityOut	26.4(18–36)	19(16-20)	0.0%0pp	0%0pp	0%	0%	83.4%2.3pp
Coventry CityOut	24.6(15–35)	19(16-20)	0.0%0pp	0%0pp	<0.1%	<0.1%	86%10.1pp

Get the data: season table as CSV · raw JSON on GitHub

Citizen of Nowhere Picks

Call every game of the matchweek blind, rank your confidence, and see whether you out-predict this model week after week. The model plays its own card, graded by the same rules.

Play Citizen of Nowhere Picks

Where these numbers come from

Ratings blend this site's own club data with a market signal, replayed forward 20,000 times against the real remaining 2026-27 season. Last generated 2026-09-15, after 40 matches played. Fixture picks blend the model with the posted line and are graded against results above; the Brier scores on this page and on the Ledger use that same graded record.

How the model works

Each club's attack and defence are goal rates per game from its last three league seasons (2025-26, 2024-25, 2023-24), recency-weighted, with the current campaign's real goals folded in as it plays out. The promoted clubs' Championship rates are translated with factors calibrated on every promoted side in this site's hub archive (75 club-seasons: attack ×0.637, goals conceded ×1.839). On top of the site data sits a market signal: de-vigged match odds (football-data.co.uk closing/posted odds (E0/E1)) fitted into team ratings and blended in at weight 0.45. Played matches count as real results; every remaining fixture is simulated with Poisson goals (league scoring rate 1.4423per team-game, home advantage ×1.11), each simulated season drawing every club's strength from a distribution (σ 0.15) rather than a fixed number. Fixture picks blend model and market 50/50 and are graded against results above. Site-data goal rates blended with market-implied team ratings; actual results folded in and only the remaining fixtures simulated, with correlated home-advantage and per-team season noise sized to an adaptive sigma and common random numbers.

Uncertainty shrinks as the season does - the spread of outcomes each simulated season draws from narrows week by week as fewer matches remain, and widens back out for a club the stats and the market disagree about most. Each simulated season also draws one correlated home-advantage error for the whole league and one for each club, rather than treating every match as its own coin flip - real campaigns run hot or cold together, not independently.

The title race

The next fixtures, called

Every club, every outcome

🎯 Citizen of Nowhere Picks

Where these numbers come from

Citizen of Nowhere Picks