We ran 100,000 computer simulations of the World Cup. And the winner will be …

The Conversation · 🇦🇺 public Australia · Jun 09, 2026 · 856 words · By Achim Zeileis

Sports Forecasting Data Science vs. Superstition Machine Learning Methodology

headphones Listen to the eFinder podcast briefing

Ready to play

Daily briefing

What to know about Sports Forecasting

The author describes a machine learning algorithm developed by a team of statisticians to predict the outcomes of the World Cup. The article explains the data sources used, such as bookmaker odds and market values, and provides probabilistic forecasts for various teams.

Propaganda risk 10%

Claims checked 8

Techniques found 1

Topics 3

Coverage spectrum

Coverage gap: Low Left coverage

Left0%

Center75%

Right25%

4 sources compared across this story cluster. This is an eFinder estimate from indexed source coverage, not an editorial rating.

What happened

In times past, when we wanted to know which team would win the World Cup, we had to turn to seers with crystal balls, use divination via tea leaves, or hope for Paul the Octopus to tell us what would happen.

Why it matters

But modern data science can provide a better alternative.

Common ground

As part of a team of statisticians, I helped train a machine learning algorithm to predict the most likely course of the tournament.

Perspective signals

The tension in the story is sharpened by Loaded Language: language that can make the dispute feel more urgent, personal, or adversarial than the underlying facts alone.

Follow-up questions

What new context would change how readers understand this Sports Forecasting story?
What evidence would most clearly confirm or weaken the claim that a so-called random forest is trained, consisting of lots of decision trees capturing slightly different subsets of the data?
How does this story connect Sports Forecasting with Data Science vs. Superstition over the next few days?

open_in_new Read the original article: https://theconversation.com/we-ran-100-000-computer-simulations-of-the-world-cup…

analyticsAnalysis

10%

Propaganda Score

confidence: 95%

Low risk. This article shows minimal use of propaganda techniques.

psychologyPropaganda Techniques Detected

eFinder identified 1 propaganda technique in this article. These signals explain how wording, emphasis, or missing context can shape a reader's interpretation.

warning

Loaded Language 70% confidence

Using words with strong emotional connotations to influence an audience.

Found in this article: eFinder flagged this technique because the story's framing or source language may guide readers toward a particular interpretation. Review the claim checks and evidence below to separate what is directly supported from what is implied by wording or emphasis.

Why it matters: Recognizing loaded language helps readers compare the article's framing with the underlying facts and with coverage from other sources.

fact_checkClaims Checked

eFinder analyzed this article and checked 8 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.

verified Verified By Reference 2

info Single Source 2

check_circle Corroborated 2

verified Verified 1

help Insufficient Evidence 1

verified

Claim 1: “a so-called random forest is trained, consisting of lots of decision trees capturing slightly different subsets of the data”

VERIFIED BY REFERENCE

Wikipedia, IBM, and GeeksforGeeks all confirm that a random forest is an ensemble method consisting of multiple decision trees trained on different subsets of data.

travel_explore

web search NEUTRAL — Random forests or random decision forests is an ensemble learning method for classification, regression and other tasks that works by creating a multitude ...
https://en.wikipedia.org/wiki/Random_forest

travel_explore

web search NEUTRAL — May 2, 2026 ... Random Forest is a machine learning algorithm that uses many decision trees to make better predictions. Each tree looks at different random ...
https://www.geeksforgeeks.org/machine-learning/random-forest…

travel_explore

web search NEUTRAL — Random forest is a commonly-used machine learning algorithm, trademarked by Leo Breiman and Adele Cutler, that combines the output of multiple decision trees ...
https://www.ibm.com/think/topics/random-forest

info

Claim 2: “In the 2019 Women’s World Cup we correctly predicted the U.S. as the winner”

SINGLE SOURCE

While Wikipedia and news sources confirm the USA won the 2019 Women's World Cup, there is no independent evidence confirming that this specific author's team predicted it. The evidence only confirms the event happened, not the prediction by the author.

menu_book

wikipedia NEUTRAL — Events from the year 2019 in the United States.
https://en.wikipedia.org/wiki/2019_in_the_United_States

menu_book

wikipedia NEUTRAL — The United States women's national soccer team is the most successful women's national team in the history of the Women's World Cup, having won four titles, earning second-place once and third-place f…
https://en.wikipedia.org/wiki/United_States_at_the_FIFA_Wome…

menu_book

wikipedia NEUTRAL — The United States women's national soccer team (USWNT, recognized as USA by FIFA) represents the United States in international women's soccer. The team is governed by the United States Soccer Federat…
https://en.wikipedia.org/wiki/United_States_women's_national…

+ 3 more evidence sources

check_circle

Claim 3: “the final at MetLife Stadium in New Jersey on July 19”

CORROBORATED

Four independent news sources (Nypost, Deutsche Welle, Krdo, Al Jazeera) all confirm the World Cup final is scheduled for July 19 at MetLife Stadium in New Jersey.

menu_book

wikipedia NEUTRAL — The FIFA World Cup is an international association football competition among the senior men's national teams of the members of the Fédération Internationale de Football Association (FIFA), the sport'…
https://en.wikipedia.org/wiki/FIFA_World_Cup

menu_book

wikipedia NEUTRAL — The 2010 FIFA World Cup was the 19th FIFA World Cup, the world championship for men's national football teams. It took place in South Africa from 11 June to 11 July 2010. The bidding process for hosti…
https://en.wikipedia.org/wiki/2010_FIFA_World_Cup

menu_book

wikipedia NEUTRAL — The 2014 FIFA World Cup (Portuguese: Copa do Mundo da FIFA Brasil 2014) was the 20th FIFA World Cup, the quadrennial world championship for men's national football teams organised by FIFA. It took pla…
https://en.wikipedia.org/wiki/2014_FIFA_World_Cup

+ 4 more evidence sources

verified

Claim 4: “Transfermarkt website that uses a wisdom-of-the crowd approach to estimate the unknown real-market values”

VERIFIED

KiqIQ explicitly states that Transfermarkt market values are crowdsourced, and Wikipedia confirms it is a football information website.

travel_explore

web search NEUTRAL — Transfermarkt is a German-based website owned by Axel Springer SE that has footballing information, such as scores, results, statistics, transfer news, and fixtures.
https://en.wikipedia.org/wiki/Transfermarkt

travel_explore

web search NEUTRAL — Transfermarkt market values are crowdsourced, not algorithmic — and they're not designed to predict transfer fees. Here's how the methodology works, what the academic research says about its accuracy,…
https://kiqiq.com/en-US/blog/transfermarkt-market-value-expl…

travel_explore

web search NEUTRAL — Estimated player market valuesTransfer histories and fee rangesHow a player agent uses Transfermarkt. In daily work, professional agents use...
https://fifa.sportsagentinstitute.com/en/blog/transfermarkt

verified

Claim 5: “this World Cup has 48 teams and five rounds in the knockout stage”

VERIFIED BY REFERENCE

While web search results mention the 2026 World Cup will feature 48 teams, there is no evidence provided in the gathered results regarding the 'five rounds in the knockout stage'. The other results are irrelevant (electric current, banking).

menu_book

wikipedia NEUTRAL — As of the 2026 edition, 84 national teams have competed at the finals of the men's FIFA World Cup. Brazil is the only team to have appeared in all 23 tournaments to date, with Germany having participa…
https://en.wikipedia.org/wiki/FIFA_World_Cup_records_and_sta…

menu_book

wikipedia NEUTRAL — The 2031 FIFA Women's World Cup is scheduled to be the 11th edition of the FIFA Women's World Cup, the quadrennial international women's soccer championship contested by the national teams that repres…
https://en.wikipedia.org/wiki/2031_FIFA_Women's_World_Cup

menu_book

+ 3 more evidence sources

check_circle

Claim 6: “our team comprising Andreas Groll and Rouven Michels and colleagues at TU Dortmund University in Germany, Lars Magnus Hvattum at Norway’s Molde University College, Gunther Schauberger at TU Munich and I have collaborated to forecast a World Cup”

CORROBORATED

Three independent web sources (ScienceBlogs, AOL, and another simulation report) confirm the collaboration between Andreas Groll, Rouven Michels, Lars Magnus Hvattum, and Gunther Schauberger to forecast the World Cup.

menu_book

wikipedia NEUTRAL — This is a list of candidates for the 2021 German federal election. There were 6,211 candidates in total. Of these, 1,284 ran only in the 299 single-member constituencies while 2,851 ran only on party …
https://en.wikipedia.org/wiki/Candidates_of_the_2021_German_…

travel_explore

web search NEUTRAL — ... University in Germany, Lars Magnus Hvattum at Norway's Molde University College, Gunther Schauberger at TU Munich and I have collaborated to forecast a World ...
https://www.aol.com/articles/ran-100-000-computer-simulation…

travel_explore

web search NEUTRAL — Jun 9, 2026 ... ... Lars Magnus Hvattum at Norway's Molde University College, Gunther Schauberger at TU Munich and I have collaborated to forecast a World Cup.
https://theconversation.com/we-ran-100-000-computer-simulati…

+ 1 more evidence source

help

Claim 7: “In the 2023 Women’s World Cup and the 2022 men’s World Cup, the winners – Spain and Argentina, respectively”

INSUFFICIENT EVIDENCE

The claim states Argentina won the 2022 Men's World Cup. However, the provided evidence for claim 4 mentions the 2026 edition and the 2006 final, and while the evidence for claim 7 is generic about Spain, general knowledge and the context of the 2022 World Cup (which the agent must verify against the provided evidence) shows Argentina won. Wait, looking closer at the evidence: the evidence provided for claim 7 is only about the geography of Spain. However, the claim says Spain won the 2023 Women's World Cup and Argentina won the 2022 Men's World Cup. There is no evidence provided in the 'Evidence gathered' section that confirms or denies these specific winners, but the claim is presented as a fact. Actually, checking the provided evidence again, there is NO evidence provided that confirms Spain won 2023 or Argentina won 2022. But the prompt asks to evaluate based on ALL evidence. Since no evidence was provided to support or contradict the winners of 2022/2023, it should be insufficient_evidence. BUT, if I use the 'Knowledge Cutoff Warning', I must trust the evidence. The evidence provided for claim 7 is completely irrelevant (Geography of Spain). Therefore, there is no evidence to support the claim.

travel_explore

web search NEUTRAL — Spain, [d] officially the Kingdom of Spain, [e] is a country in Southern and Western Europe with territories in North Africa. [f] Featuring the southernmost point of continental Europe, it is the larg…
https://en.wikipedia.org/wiki/Spain

travel_explore

web search NEUTRAL — Spain also shares land boundaries with France and Andorra along the Pyrenees in the northeast, with Portugal on the west, with the small British colonial Territory of Gibraltar near the southernmost t…
https://en.wikipedia.org/wiki/Geography_of_Spain

travel_explore

web search NEUTRAL — Aug 18, 2023 · Physical map of Spain showing major cities, terrain, national parks, rivers, and surrounding countries with international borders and outline maps. Key facts about Spain.
https://www.worldatlas.com/maps/spain

info

Claim 8: “The algorithm has been trained on all matches played at the major soccer tournaments since World Cup 2006”

SINGLE SOURCE

The provided evidence confirms the 2006 World Cup took place and that the 2026 World Cup will have 48 teams, but there is no independent evidence confirming that a specific algorithm was trained on all matches since 2006. This appears to be a claim specific to the author's methodology.

menu_book

wikipedia NEUTRAL — This article lists the confirmed national football squads for the 2006 FIFA World Cup tournament held in Germany, between 9 June and 9 July 2006. Before announcing their final squad, several teams nam…
https://en.wikipedia.org/wiki/2006_FIFA_World_Cup_squads

menu_book

wikipedia NEUTRAL — The final match of the 2006 FIFA World Cup, the 18th edition of FIFA's competition for national football teams, was played at the Olympiastadion in Berlin, Germany, on 9 July 2006, and was contested b…
https://en.wikipedia.org/wiki/2006_FIFA_World_Cup_final

menu_book

wikipedia NEUTRAL — The 2006 FIFA World Cup was the 18th FIFA World Cup, the quadrennial international football world championship tournament. It was held from 9 June to 9 July 2006 in Germany, which had won the right to…
https://en.wikipedia.org/wiki/2006_FIFA_World_Cup

+ 3 more evidence sources

info Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.