Data scientist Taylor Larkin crunched the numbers, and here are his probability picks for which heads will roll in season eight.
Why we care: Nobody was prepared for it when Ned Stark (Sean Bean) literally lost his head in the first season of Game of Thrones. (Well, nobody except for the thousands who’d actually read the books and were actively anticipating what face you’d make when you watched that shocking execution.) Ned had been set up as the moral center of the series. His death was a shot across the audience’s bow, signaling that no character was safe. Valar morghulis, etc., ad infinitum.
By now, audiences are keenly aware of the eminent fallibility of the sprawling cast’s every member. The high-profile deaths have arrived with such regularity that one could conceivably predict who goes next. In fact, somebody did.
Several predictive analyses have come before, but data scientist Taylor Larkin wanted to take a crack at it himself. Larkin took info on the show’s bajillions of characters, scraped from a fan-made wiki–including data points like house, gender, nobility status, age, and number of relatives already killed–and used automated machine learning from DataRobot to determine who is most likely to die in the show’s final season, which is scheduled to premiere in April 2019. (The entire complicated process is detailed in full here.)
Have a look at the results below, but keep in mind that the data comes from the Song of Fire and Ice books, rather than the show, which has taken some necessary liberties in its later seasons.
Daenerys Targaryen–83.77% chance of death
Jaime Lannister–72.91% chance of death
Tyrion Lannister–70.76% chance of death
Bran Stark–66.02% chance of death
Cersei Lannister–60.39% chance of death
Jon Snow–58.99% chance of death
Euron Greyjoy–54.95% chance of death
Sansa Stark–50.28% chance of death
Arya Stark–49.04% chance of death
Gendry–39.87% chance of death
Now, if only the algorithm could predict when George R.R. Martin will finish The Winds of Winter, the achingly anticipated final book in the series.
Register for your ticket here: https://www.thedatasciencesummit.com/book-your-tickets/