Detecting strategic moves in HearthStone matches

Boris Doux (1) , Clément Gautrais (1, 2) , Benjamin Negrevergne (1)

1 LACODAM - Large Scale Collaborative Data Mining
2 UR - Université de Rennes

In this paper, we demonstrate how to extract strategic knowledge from gaming data collected among players of the popular video game HearthStone. Our methodology is as follows. First we train a series of classifiers to predict the outcome of the game during a match, then we demonstrate how to spot key strategic events by tracking sudden changes in the classifier prediction. This methodology is applied to a large collection of HeathStone matches that we have collected from top ranked European players. Expert analysis shows that the events identified with this approach are both important and easy to interpret with the corresponding data.

Domaines: Intelligence artificielle [cs.AI]; Apprentissage [cs.LG]; Base de données [cs.DB]

Boris Doux, Clément Gautrais, Benjamin Negrevergne. Detecting strategic moves in HearthStone matches. Machine Learning and Data Mining for Sports Analytics Workshop of ECML/PKDD, Sep 2016, Riva del Garda, Italy. ⟨hal-01412432⟩