Game of Thrones has long made fans understand that no character is safe. George R. R. Martin seemingly kills any character which he sees, doing away with what’s expected and instead putting the characters through a meat grinder as we make our way to the eventual conclusion of the tale. There’s always lots of speculation about who’ll make it to end of each book and even who’ll still be alive by the time we see the end of book 7. It’s all just been theories on internet message boards with nothing to back it up beyond obscure clues and references within the various books themselves.

Now Richard Vale, a lecturer in the Statistics Department at the University of Canterbury, used mathematical models to predict who lives and dies in the next two Game of Thrones novels. Vale isn’t able to predict what may happen to any one character, but he’s using supposed mathematical trends to predict who will still be alive and a focus of the story as Winds of Winter comes to a close by using their previous number of POV chapters to infer how many chapters they and other characters will have in the next two books.

For a slightly technical look at Vale’s process, take a look at this excerpt from the write up on the Physics arXiv blog:

Vale begins with a single table of data which summarizes the number of chapters that each character has starred in so far. For example, the character Jon Snow starred in nine chapters in the first book, eight in the second, 12 in the third, none in the fourth and 13 in the fifth. The character Brienne starred in 8 chapters in the fourth book but in none of the others. And so on.

The question that Vale sets out to answer is what can be predicted about future books based only on this data from the existing ones. And his approach is entirely statistical so it does not include common sense assumptions such as the idea that a character killed off in the past is unlikely to star in the future.

Of course, Vale has to make a number of assumptions about the statistical nature of the data. For example, he assumes that the chapters in which a character stars follows Poisson distribution, which is one of the simplest to handle mathematically. It is based on the idea that events in a given time interval occur independently, like the number of decay events per second from a radioactive source, and are not related by some deeper connection.

Having created a model, Vale then runs a computer program to find the parameters in the model that best fit the data. And having found the best fits, he then uses the model to find the probability distributions of the number of chapters that each character will star in in book 6 and book 7. (He points out that book 7 is less interesting because the probabilities can be sharpened after the publication of book 6).

Some of the predictions are pretty straightforward. Ned Stark, logically, has a very small chance of having any POV chapters in the next two books because he’s been absent for the last four. Tyrion and Daenerys have a much higher change of having POV chapters in the next two books as they’ve had several in all of the books, excluding A Feast For Crows. Vale even makes a prediction about a certain bastard who has an ambiguous ending in A Dance With Dragons. 

Vale is the first to admit that this model is inherently flawed because it’s using only a small set of data and doesn’t account for new characters and date to be added. Even more worth noting is that models such as this really only work in predictable systems, and Martin has proven that he’s anything but predictable.

It’s always really interesting and exciting to see two vastly different kinds of nerdery collide and produce something really cool. Never did I think I would see mathematical models applied to Game of Thrones, but the internet is a wondrous place. For those that may be a bit more analytic and want to check out the full findings of the modeling, head here.

Analytic or not, look at page 10 of the report to find out what Vale thinks happens after the end of A Dance With Dragons. Prepare yourself.

Source: Physics arXiv Blog

Category: Books, Cool Stuff, TV

Tags: , , , ,