WASHINGTON. Sunday, April 14, 2019 marks the beginning of the end for HBO’s already legendary epic series, Game of Thrones. (Aka, GoT.) Shorter in number but longer in running time, avid GoT fans will finally get to see who wins the game. And the Iron Throne. While the outcome is anyone’s best guess at this point, some intrepid computer science students studying at the Technical University of Munich (TUM) in Germany may be ahead of the curve when it comes to predicting character survival odds in Game of Thrones S8, the series’ final season.
Back in 2016, “[a]s part of their class project the students developed applications that scour the web for data on the Game of Thrones and crunch the numbers. They then put together a website that reports which characters are most likely to die in the upcoming sixth season of the TV series.” Fans will find their final calculations for the outcome of Game of Thrones S8 provocative. And fun to argue about.
How’d they do it?
“The class decided to create a machine learning algorithm designed to analyze the characters in George R.R. Martin’s epic fantasy and look for markers that indicate impending doom. To do so, it relied heavily on the crowdsourced A Wiki of Ice and Fire.
“The students identified more than 2,000 characters in the series. They took note of a character’s gender, age, social standing, house, which books the character appeared in and whether or not the character is still alive in the context of the story. They designed an algorithm to take all this information into account to see if there are common elements that indicate a particular person is more or less likely to die.
“The students used an array of machine learning algorithms to answer these questions. The algorithm, which accurately predicted 74 percent of character deaths in the show and books, has many surprises in store, placing a number of characters thought to be relatively safe in grave danger.”
Algorithms successfully predict the return of a major Game of Thrones figure
Compiled after GoT Season 5 was completed, the team employed one algorithm to answer the most pressing issue for the series’ most avid fans. Could Jon Snow – killed by his own men in the shocking finale to Season 5 – somehow return?
After the computer crunched the data, the answer turned out to be a rousing, statistically supported YES. And (spoiler alert for those who haven’t got to this point yet) that’s exactly what happened in Season 6, much to the great relief of Jon’s legion of fans. Fans not afraid of spoilers, even virtual ones, might be tempted to get a jump on Game of Thrones S8 by seeing what those TUM computer geeks have been up to lately.
So what are the machines predicting for GoT Season 8?
According to a recent update on the Munich students’ work in progress, their algorithmic approach to the GoT data provides some interesting predictions. In fact, these predictions are a matter of life and death for the popular series’ remaining characters.
“The algorithms developed now by the students predicts that Daenerys Targaryen has the highest chance (99%) of surviving the harrowing GoT world. Her Hand of the King, Tyrion Lannister, also has a promising 97% survival rate.
“Survival rates are predicted using longevity analysis – a technique similar to scientific studies that examine the effects of treatments and complications on cancer patients.”
Algorithms: Not just for Wall Street traders anymore
In recent years, complex financial algorithms deployed by high-speed computerized traders and investment firms on Wall Street have controversially transformed the way stock markets react, injecting news headlines and public opinion, real or apparent, into the buy or sell equation.
Likewise, in addition to stats compiled from the original GoT books and now the HBO Series – which at times has either simplified the saga for dramatic purposes or otherwise sharpened the story arc to enhance the characters and the visuals – the students algorithmic approach to GoT also tracks and analyzes Twitter user sentiments on hundreds of GoT characters. It’s all in an effort to synthesize the considerable amount of available info in order to sharpen the accuracy of the students’ ultimate projections, which culminate with Game of Thrones S8.
Big data: Also a big deal and a key to accurate predictions
While the TUM students’ project may seem to be a trivial pursuit, it’s not. For example, a number of college English majors decide to deploy the writing and analytical skills they develop in literary analysis to the study of law. Critical analysis and precise writing are transferable skills. Likewise, the skillful creation of algorithms to closely predict the outcomes of a TV series. That skillset, too, is easily deployable to any number of high paying positions in major corporations.
Notes the already-cited TUM news release on the topic:
“‘Data mining and machine learning are tools that enable digital medicine to benefit from modern biology for diagnosis, treatment and prevention of disease. Turning to such a “real life” challenge created a didactical jewel, winning students for these subjects,’ summarizes Burkhardt Rost, Professor of Bioinformatics at the Technical University of Munich. ‘And the interactive visual maps created in the project might open a new approach to data visualization that we will follow up scientifically.’”
While this all may seem like seriously nerdy stuff – which indeed it is – tailoring computational analysis to track a popular and exciting TV series is nearly like getting to the bottom of plot, character and analysis in a popular novel. It’s also a far more enjoyable way to explore the usefulness of an increasingly important bag of computerized analytical tools. That’s certainly what TUM professor Guy Yachdav thinks.
Maybe it’s really okay to explore algorithms and big data just for fun
“‘This project has been a lot of fun for us,’ says Dr. Guy Yachdav, who led the class and conceived the project. ‘In its daily work, our research group focuses on answering complex biological questions using data mining and machine learning algorithms. For this project we used similar techniques. Only this time the subject matter was a popular TV show. The epic scale of the worlds created by George R. R. Martin provides an almost endless resource of raw multi-dimensional data. It provided the perfect setting for our class.’”
As an extra-added attraction, however, the TUM class has been letting the public in on its complex algorithmic fun. You can check their work out right here at https://got.show. Go on, give it a try. Unless you worried that the machine’s prediction of Game of Thrones S8 outcomes might come too close to reality.
Here on this attractive, interactive site, you’ll find current characters and their chance of survival. At least according to the TUM students’ algorithms. You’ll also learn how the algorithm or algorithms managed to get to the current conclusions.
“For instance, being born in Winterfell to the House of Stark as well as only being married once seems to increase the chances of Sansa Stark to be eliminated in the upcoming season; her predicted likelihood of death is 73%.
“Fans interested in exploring the differences between the plot of the TV show and the story told by the books underlying the TV series, can find a side by side comparison of details about characters, including age, status (dead vs. alive) and longevity prospects.”
We’ll turn back to Professor Rost for the next-to-final word…
“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 just one little bit of potential future shock
I.e., carrying out creative academic projects like TUM’s GoT site will likely involve moving to a different toolkit.
As for now, however, TUM’s GoT site is the most enjoyable GoT predictive site on the Internet. Assuming that thos TUM algos have really got the goods on the show’s ultimate outcome. We’ll all start finding out. Tonight.
— Headline image: Truth? Or consequences? Screen grab of current splash screen displayed on “Game of Thrones” official homepage. Good luck, Jon. You’ll need it! (Image and site copyright 2019 by HBO. Fair use in Season 8 preview piece)