Real-Time Win Probability in League of Legends

March 25, 2022 10:00 am EDT

Daniel Owens and Danny Simon from Qarik

Recently, Qarik’s Data Science team investigated machine learning models within the context of predicting the outcomes of esports games, focusing on League of Legends (LoL). In this virtual coffee, we will discuss the approaches we took in an effort to model the complicated phenomena of LoL games, including what we outlined in our past blog.

In this virtual coffee we will discuss:

  • Goals of the project
  • Data science techniques and processes (where to begin and how to proceed)
  • Dynamic Time Warping (DTW) – a rich framework for comparing different time series
  • Feature and model selection
  • Demystifying the black box (SHAP)

Note: this virtual coffee will not be recorded so guests can speak freely.