Loading…
Back To Schedule
Saturday, October 20 • 1:00pm - 1:30pm
Latent Dirichlet Allocation on Player Session Behavior in Gaming

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
As data scientists at Riot Games, our goal is to focus on providing the best player experience possible. Understanding how players play individual sessions and how their styles evolve over time is key to evaluating our products and helps make decisions for future designs. In this talk, I will present how we use Latent Dirichlet Allocation (LDA), a three-level hierarchical Bayesian model, to identify major session topics in League of Legends and how we construct a player segmentation with session clusters.

Speakers
avatar for Ran Cao

Ran Cao

Data Scientist, Riot Games
Ran Cao is a Data Scientist for League of Legends at Riot Games. League of Legends is one of the most-played games in the world, with frequent updates to expand the possibilities for players. Her data science background has focused on Bayesian modeling across genetics, public policy... Read More →


Saturday October 20, 2018 1:00pm - 1:30pm PDT
Ballroom # 409