I can’t believe am writing about this… Mainly B/C i hate GOT and all it’s followers (i watch it loosely when am completely out of walking dead content ? ). Yes am a #twd (the Walking Dead) and American gods super fun. Well, it’s pretty awesome how someone would go to the extent of predicting deaths of fictional characters… More so creating a computer algorithm to do that( pretty hard, huh?)
Warning ⚠ : Possible spoiler alert
So, Milan Janosov, a Ph.D. student at the Center for Network Science at the Central European University, claims to have created an algorithm that can predict the likelihood of a will-be-dying character of this unpredictable show. with some graph algorithm that consists of approximately 400 nodes and 3000 edges, he can predict the death of your favorite character. A model called Support Vector Machine (SVM), is a supervised learning model used for finding the probability of the surviving character that will die before the show ends next year in 2018.
Apparently, he used scene analysis to create seven different network-based features based on their various dimension of social importance. He called it “the elementary unit of social interaction”. He combined this with the traits of the 61 character that previously died in this show. Better predictions can be made by including features such as gender and Nobel clans they belong to.
So guess who’s least likely to die on the show based on the model? Theon Grejoy, popularly known as Reek, with a probability of just 0.05. The character most likely to die is Tyene Sand, bastard daughter of Prince Oberyn Martel with the probability of 0.95. Daenerys Targaryen who is one of the most favorite characters of the show is second most likely to die with the probability of 0.91. Tyrion Lannister, on the other hand, has a 0.52 chance of dying, according to the model.
The model is part of a research group that focuses on answering complex biological questions using data mining and machine learning algorithms.