The last season of »Game of Thrones« is about to start and fans all over the world are asking themselves: Who will climb the Iron Throne? Students of TUM already wanted to know before the final and programmed algorithms of machine learning to make survival prognoses for the characters.
Game of Thrones is known for the fact that characters don't have a very high chance of survival. The finale is now approaching in big steps and of course it's especially exciting: Who will survive and become king? Students at the Technical University of Munich also dealt with this question. They developed a computer science application that searches the Internet for data about Game of Thrones and uses artificial intelligence algorithms to process the numbers. This enables them to predict the chances of survival of the individual Game-of-Thrones characters.
According to the algorithm, Daenerys Targaryen has the highest chance (99 percent) of surviving the GoT world. But also the right hand of the king, Tyrion Lannister, has a promising survival rate of 97 percent.
The survival rates are predicted with the help of longevity analysis. The technique is similar to scientific applications that investigate the effects of treatments and complications in cancer patients.
The complete list of characters and their chances of survival is available online. Experienced Game of Thrones fans can take a close look at the prediction technique on the website. For example, the fact that Sansa Stark was born in Winterfell in the House of Stark and was married only once seems to increase her chances in the coming season. Her predicted probability of death is only 73 percent.
Fans who want to explore the differences between the plot of the TV series and the story from the books will find a direct comparison of the characters, including age, status (dead vs. alive) and survival predictions.
The leading mentor of the course, Dr. Guy Yachdav, says: »While the task of predicting survival chances for Game-of-Thrones characters is based on data from the world of fantasy, in reality the same artificial intelligence techniques are used and have a strong impact on our everyday lives.«
Professor Burkhard Rost, Head of the Department of Bioinformatics at TUM, adds: »The combination of teaching and passion is a brilliant way to provide students with experience in using these new tools and to prepare them to create great new applications themselves after graduation«.