These are the results that our AI robot Kashef predicted for the three matches on Monday.

Kashef, our artificial intelligence (AI) to the 2022 World Cup what Paul the Octopus was to the 2010 edition.

Kashef played with historical data and performance to predict the results of each game, right up to the final.

Here are the match predictions for the three matches on Monday:

Who: England vs Iran, Group B
Where: Khalifa International Stadium
When: Monday, November 21 (4:00 PM local time, 1:00 PM GMT)


Kashef predicts a victory for England this afternoon. Good start for Harry Kane’s team if everything goes according to Kashef’s plans.

Read the match example here.

Who: Senegal against the Netherlands, group A
Where: Al Thumama Stadium
When: Monday 21 November at 16:00 GMT


The European team also comes out on top in the second game of the day, says Kashef. Senegal, remember, is the reigning African champion, so they would like to prove Kashef wrong today.

Read the match example here.

Who: USA vs Wales, Group B
Where: Ahmed bin Ali stadium
When: Monday November 21, 22:00 (19:00 GMT)

United States

Will Gareth Bale be happy with Kashef this morning? Probably not. Wales took a long time to rejoin the World Cup. They wouldn’t want to start at a loss there.

Read the match example here.

How does our AI match predictor work?

Al Jazeera collected more than 200 statistics measuring the performance history of the 32 teams participating in this year’s World Cup.

These include number of wins, goals scored, FIFA rankings and more, from matches played over the past century, totaling over 100,000 records.

We have gone through these Vertex AI from Google Cloud, which produces state-of-the-art models – using Google Brain – that use Efficient Neural Architecture Search (ENAS) to find the best prediction model. The data pipeline is built with GCP BigQuery.

After each match, the model is run again to predict the outcome of the next match up to and including the final.

Predicting match results is not easy. External factors such as team morale or player fitness make a big difference to how the game plays out.

Based on our simulations for the 2014 and 2018 World Cup tournaments, Kashef is about 71 percent accurate, with an area under the curve (AUC) of about 67 percent.

Source link

By wy9m6

Leave a Reply

Your email address will not be published. Required fields are marked *