Who will survive in Game of Thrones season 8? An new application using a machine learning algorithm has predicted Game of Thrones spoilers including the likelihood of popular characters’ deaths.
Students attending a computer science seminar at the Technical University of Munich (TUM) worked on the Game of Thrones season 8 predictions using a machine learning algorithm. The students developed an application that trawls the web for Game of Thrones (GoT) data and uses a set of AI algorithms they created.
— Game of Thrones (@GameOfThrones) 5 April 2019
Who has the best chance of sitting on the Iron Throne?
The machine learning algorithm developed now by the students predicts that:
• Daenerys Targaryen has the highest with 99% chance of surviving Game of Thrones; and
• Tyrion Lannister also has a high chance of survival, 97%.
According to the algorithm, the characters with the highest chance of dying next are:
• Bronn, who has a 93.5% chance;
• Gregor Clegane, with an 80.35%; and
• Sansa Stark, with a 73.35% chance.
The full list of survival rates
The survival rates for Game of Thrones season 8 were predicted using longevity analysis. This is a technique similar to scientific studies that examine the effects of treatments and complications on cancer patients.
The full list of characters and their survival chances is available online.
How accurate is the prediction?
Although the algorithm can only predict what will happen in Game of Thrones season 8, in 2016 before the airing of Season 6, students on the same course created an algorithm that was able to accurately predict Jon Snow’s resurrection.
The lead mentor of the class, Dr. Guy Yachdav, commented: “while the task of predicting survival chances for Game of Thrones characters relies on data taken from the world of fantasy, the exact same artificial intelligence techniques are used in the real world and are having a powerful impact on our everyday lives.”