← Schedule

Group D · Matchday 9 · 2026-06-19

Turkey vs Paraguay

Santa Clara, United States · neutral venue

Full time TUR 0–1 PAR

The agent called Turkey (40%) — Worse than the model call wrong

The forecast below is what the agent published before kickoff.

Most likely scoreline

0–0 14.6%

36.9%

TUR win

29.4%

Draw

33.6%

PAR win

Top scorelines

0–0 14.6%
1–0 13.1%
0–1 12.4%
1–1 11.2%

Total goals

0 to 10 goals · most likely → tallest

The agent’s call

3-agent ensemble · deepseek-chat

TUR win

40.0%

Draw

30.0%

PAR win

30.0%

Turkey's recent form is stronger (over-performing vs tougher opponents) and their squad value is significantly higher (2.5x) with key players at elite clubs. Paraguay's opening loss and Enciso's injury uncertainty add to their disadvantage. The model's near-even split underestimates Turkey's edge; I shift from 37% to 40% home win, reducing away win from 34% to 30%. Both teams scored modestly in their openers (Turkey 0, Paraguay 0) and the model expects low goals (Turkey 1.14, Paraguay 1.06). Turkey's slight offensive edge and Paraguay's defensive resilience suggest 1-0 or 1-1 as most likely, with 0-0 also plausible.

What the agent weighed

Recent form

Turkey over-performing expectations by +0.50 pts/match vs opponents averaging rank #35; Paraguay in line with expectations (-0.12) vs opponents rank #50. → favours Turkey
Head-to-head

No previous meetings between Turkey and Paraguay. → no bearing
Squad market value

Turkey ranks 15th (70th pct), Paraguay ranks 28th (43rd pct); Turkey's squad is ~2.5x more valuable. → favours Turkey
Key players

Turkey's key players include Çalhanoglu (Inter), Güler (Real Madrid), Yıldız (Juventus); Paraguay's marquee include Enciso (Strasbourg), Gómez (Palmeiras), Almirón (Atlanta United). Turkey's players at higher club level. → favours Turkey
Injuries / availability

No injuries reported for either side. → no bearing
Recent news

Turkey lost 2-0 to Australia in their World Cup opener (Reuters, AP). Paraguay lost star Julio Enciso to injury before their match vs USA (NY Post), but Enciso is listed in key players and no news confirms he is out for this match; Paraguay lost 2-0 to USA (Bleacher Report). → favours Turkey (Turkey's loss was competitive; Paraguay's loss and Enciso injury uncertainty weaken them)
Match-day conditions

Levi's Stadium: 19.2°C, clear, humidity 65%, wind 15.6 km/h. Mild conditions, no extreme heat or altitude. → no bearing
Model vs market

Statistical model gives Turkey 37% win, draw 29%, Paraguay 34% win. No betting market lines supplied. → no bearing (no market to compare)

What the agent chose to investigate

The agent decided what to check on tavily — 9 sources kept:

“Turkey injury news June 2026” TUR · 3 hits
Late fitness updates could change key player availability.
“Paraguay injury news June 2026” PAR · 3 hits
Late fitness updates could change key player availability.
“Turkey vs Paraguay Santa Clara weather forecast June 20 2026” match · 3 hits
Weather conditions like heat or rain can affect match dynamics.

Agent scorelines

1–0 19%
1–1 17%
0–0 15%
0–1 14%
2–1 13%
2–0 12%

generated 2026-06-19

Last 5 — TUR

+0.48 pts/match vs model expectation · opp. avg #36

ESP #1 +0.7
ROM #46 +1.2
KOS #56 +1.5
VEN #47 +1.7
AUS #29 -1.4

GF / GA last 10: 21 / 15

Last 5 — PAR

-0.12 pts/match vs model expectation · opp. avg #51

MEX #20 +1.8
GRE #36 +1.9
MAR #11 -0.9
NIC #151 +0.3
USA #37 -1.1

GF / GA last 10: 13 / 13

Head-to-head (last 5)

No prior meetings in the dataset.

▸ Full score grid (7×7)

P(home goals × away goals), %

14.6

12.4

6.3

2.5

0.9

0.3

0.1

13.1

11.2

5.7

2.3

0.8

0.2

0.1

7.1

6.0

3.1

1.2

0.4

0.1

0.0

3.0

2.5

1.3

0.5

0.2

0.1

0.0

1.1

0.9

0.5

0.2

0.1

0.0

0.3

0.2

0.1

0.0

0.1

0.0

Rows = TUR goals; columns = PAR goals. Above-diagonal cells are home wins; diagonal = draws; below = away wins. Truncated at 6 — the joint mass past that is < 1 %.

Expected goals (Poisson rate, λ)

1.1

TUR

1.02

PAR

Independent-Poisson rates. W/D/L and the score grid integrate the full 13×13 joint under these two parameters.

News context — injuries, suspensions, projected XI — is not part of the model, which sees only past results.