Source: repo.fpl(latest season snapshot)
Latest season in CSV: 2025
Snapshot rule: latest available row per player for each selected team
ARS
Players shown
11
Avg price
6.9
Avg xG
2.78
Avg xA
1.92
Avg points
102.3
Matchup totals
Players shown
22
Avg price
6.5
Avg xG
3.29
Avg xA
2.04
Avg points
95.05
CHE
Players shown
11
Avg price
6.1
Avg xG
3.81
Avg xA
2.16
Avg points
87.8
LINEUPS
ARS
4-3-3
Arteta positional
CHE
4-2-3-1
Vertical runners
1David Raya Martín
2Jurriën Timber
3Gabriel dos Santos Magalhães
4William Saliba
5Piero Hincapié
6Martín Zubimendi Ibáñez
7Declan Rice
8Bukayo Saka
9Viktor Gyökeres
10Gabriel Fernando de Jesus
11Kai Havertz
1Robert Lynch Sánchez
2Marc Cucurella Saseta
3Wesley Fofana
4Jorrel Hato
5Reece James
6Moises Caicedo
7Andrey Nascimento dos Santos
8Pedro Lomba Neto
9Enzo Fernández
10Cole Palmer
11Joao Pedro
MATCH STATS
0%0%
POSSESSION %
0SHOTS0
0ON TARGET0
1.36xG1.13
0PASSES0
2.78AVG xG3.81
1.92AVG xA2.16
102.3AVG PTS87.8
£6.9mAVG PRICE£6.1m
Live simulation stats
Updates live as the match evolves.
Attack / penetration
Home AttackStyle
—
Away AttackStyle
—
Home Penetration
—
Away Penetration
—
Home Defense Style
—
Defense / build / transition
Away Defense Style
—
Home Build Style
—
Away Build Style
—
Home Transition
—
Away Transition
—
Loaded player data overview
Source: repo.fpl(latest season snapshot)
Latest season in CSV: 2025
Snapshot rule: latest available row per player for each selected team
ARS
Players shown
11
Avg price
6.9
Avg xG
2.78
Avg xA
1.92
Avg points
102.3
Live match stats
Stat
ARS
CHE
Possession
0%
0%
Shots
0 (0)
0 (0)
Passes
0 (0%)
0 (0%)
Fouls
0
0
Goals
0
0
CHE
Players shown
11
Avg price
6.1
Avg xG
3.81
Avg xA
2.16
Avg points
87.8
Home player phases
Color-coded live phase tracking.
Away player phases
Color-coded live phase tracking.
PLAYER STATS
ARS player stats
Click any column header to sort.
#
Name
Pos
$
Min
St
Pts
G
A
CS
xG
xA
Inf
IQ
Thr
1
David Raya Martín
GK
6.0
2700
30
122
0
0
14
0.00
0.06
14.2
1.1
0.0
2
Jurriën Timber
DEF
6.3
2415
27
148
3
6
13
4.71
1.52
18.3
14.9
13.0
3
Gabriel dos Santos…
DEF
7.1
2075
23
164
3
4
13
1.87
1.59
28.9
4.6
8.5
4
William Saliba
DEF
6.1
1984
23
96
1
0
10
0.88
0.61
18.1
5.7
3.3
5
Piero Hincapié
DEF
5.1
1483
17
70
1
1
4
0.33
1.35
21.8
9.6
3.2
6
Martín Zubimendi I…
MID
5.2
2524
29
114
5
1
14
2.67
2.07
19.0
11.4
8.7
7
Declan Rice
MID
7.5
2490
28
160
4
9
13
2.99
6.29
26.0
31.4
9.6
8
Bukayo Saka
MID
9.8
1905
21
130
6
8
9
6.84
5.66
25.0
32.9
34.3
9
Viktor Gyökeres
FWD
8.8
1859
23
94
10
0
10
8.23
1.76
18.1
10.2
28.5
10
Gabriel Fernando d…
FWD
6.4
304
2
17
2
0
0
1.75
0.19
29.8
7.4
61.3
11
Kai Havertz
FWD
7.3
201
2
10
0
1
2
0.31
0.06
15.9
14.9
20.1
CHE player stats
Click any column header to sort.
#
Name
Pos
$
Min
St
Pts
G
A
CS
xG
xA
Inf
IQ
Thr
1
Robert Lynch Sánch…
GK
4.9
2344
27
97
0
1
9
0.00
0.04
23.7
1.9
0.0
2
Marc Cucurella Sas…
DEF
6.0
1896
22
91
1
3
9
1.64
2.88
20.6
18.8
9.2
3
Wesley Fofana
DEF
4.4
1101
12
50
0
1
4
0.50
0.55
26.6
3.8
2.8
4
Jorrel Hato
DEF
4.6
540
5
10
0
0
0
0.30
0.41
15.9
11.2
4.0
5
Reece James
DEF
5.6
1802
19
111
2
6
8
0.90
2.69
21.4
20.7
4.9
6
Moises Caicedo
MID
5.7
2044
23
93
3
1
6
1.21
1.88
21.0
12.2
4.6
7
Andrey Nascimento …
MID
4.5
964
10
31
0
0
1
1.70
0.79
14.0
11.8
5.7
8
Pedro Lomba Neto
MID
7.0
2138
24
106
5
5
11
4.27
5.64
18.6
28.8
18.0
9
Enzo Fernández
MID
6.7
2397
27
125
8
4
8
9.93
5.64
24.3
27.9
23.1
10
Cole Palmer
MID
10.6
1236
16
92
9
2
3
8.25
1.48
31.5
17.4
29.5
11
Joao Pedro
FWD
7.6
2140
25
160
14
9
10
13.18
1.72
29.9
17.2
32.7
After The Stadium
How the Match Simulator turns data into a 90-minute control problem
The stadium shell is the visual layer. Under it, Scoutics builds a state vector from squad strength, formations, tactical style priors, venue context, and live player data, then advances the match frame by frame with a learned decision layer and a deterministic physics engine.
State Vector
Data enters as a structured football state
live state11v11
Every frame carries the ball, carrier, lane occupation, stamina, tactical role locks, and restart context. That means the engine reasons over football information, not only over visuals.
The venue choice shapes rendering and match context, while squad and FPL-derived traits shape the decision space.
Reinforcement Learning
The policy layer optimizes future reward, not only the next touch
policy searchQ(s,a)
The RL component learns that a good action is one that helps now and improves the future state. Pressing, buildup, and transition choices are scored by their long-run value, not by a single-frame heuristic.
Q(s, a) ← r + γ max_a' Q(s', a')
In plain terms: value an action by immediate reward r plus the discounted quality of the next state.
Engine Dynamics
Frame updates follow a data-driven transition function
frame physicst → t+2
Once an action is chosen, the simulator updates the world through player motion, ball physics, fouls, collisions, role intent, and tactical constraints. That creates the next state the policy will observe.
s_{t+1} = f(s_t, a_t, ε_t)
The noise term ε captures uncertainty: deflections, loose touches, interception windows, and other football chaos.
Outcome Model
Probabilities emerge from repeated state evolution
monte carloN runs
Match outcome estimates are not static odds pasted onto the page. They are generated from the same engine that drives the animation, then summarized into result and xG-style forecasts.
P(result) ≈ (1 / N) Σ 1{outcome_i = result}
Repeated simulations let the app compare model belief to market belief, which is where EV and pricing analysis begin.