Predicting kills in Game of Thrones using network properties

TL;DR

This paper explores predicting character kills in Game of Thrones by analyzing social network properties and applying link prediction techniques, achieving moderate success with degree-based indices.

Contribution

It introduces a network-based approach combining social network features with data mining to predict kills in a TV series, highlighting the effectiveness of degree indices.

Findings

Degree-based indices yield an AUC of 0.875.

Network features improve machine learning predictions.

Small dataset limits prediction accuracy.

Abstract

TV series such as HBO's Game of Thrones have seen a high number of dedicated followers, mostly due to the dramatic murders of the most important characters. In our work, we try to predict killer and victim pairs using data about previous kills and additional metadata. We construct a network where two character nodes are linked if one killed the other and use a link prediction framework to evaluate different techniques for kill predictions. Lastly, we compute various network properties on a social network of characters and use them as features in conjunction with classic data mining techniques. Due to the small size of the dataset and the somewhat random kill distribution, we cannot predict much with standard indices alone, although using them in conjunction with additional rules based on degrees works surprisingly well. The features we compute on the social network help the classic machine learning approaches, but do not yield very accurate predictions. The best results overall are achieved using indices that use simple degree information, the best of which gives us the Area Under the ROC Curve of 0.875.