With the new series out now, there’s one question on everybody’s lips: who will win the Game of Thrones? If you weren’t one of the super fans who stayed up until 2am watching the beginning of the end, don’t worry – there are no spoilers here.
But what we do have is a few suggestions – because new research from the Technical University of Munich has worked out who’s most likely to end the series perched atop that much-coveted Iron Throne.
Students at the computer science department of the university embarked on the research shortly before the new season started, developing an algorithm that “scoured the web for data [about the show] and then crunched the numbers using a set of algorithms” especially created to predict how likely each character is to survive.
Winners were predicted using “longevity analysis”, which course leader Guy Yachdav says is a technique normally used to “examine the effects of treatments and complications on cancer patients”. A slightly less worthy use of the analysis here, to be fair, but still pretty entertaining.
So who will be victorious? According to the algorithm, it’s likely to be fan favourite Daenerys Targaryen. She has the highest chance of surviving – a pretty impressive 99%.
It’s also looking good for Tyrion Lannister – his survival rate is about 97%. Not bad.
And specific traits seem to be important here, too. Being born in Winterfell to the House of Stark increases Sansa’s chances of being eliminated, researchers say – she’s got a 73% chance of being knocked out.
It’s exceptionally bad news for Bronn, too – he has a 94% chance of death, odds we would rather not reckon with personally.
The class has form, too. In 2016, it successfully predicted Jon Snow’s resurrection – so there’s a good chance that they’re on the money.
Working out who will live and who will die in Game of Thrones might be a bit of frivolous fun. But as Yachdav points out, the analysis used for the predictions might have a big impact on the world.
“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,” he said.
“The combination of passion and teaching is a brilliant way to create new tools that matter. In our course at TUM we found a fun way to teach students how to use this technology and prepare them to build the next big thing once they graduate.”
But enough of that – we’re off to the bookies.