An Empirical Bayes Approach for Estimating Skill Models for Professional Darts Players
share
We perform an exploratory data analysis on a data-set for the top 16 professional players from the 2019 season. The goal is to use this data-set to fit player skill models which can then be used in dynamic zero-sum games (ZSGs) that model real-world matches between players. We identify several problems that arise due to natural limitations in the data and propose an empirical Bayesian approach - the Dirichlet-Multinomial (DM) model - that overcomes some of these problems. We explain how the remaining problems can be finessed using the DM model with a limited action set in the ZSGs.
READ FULL TEXT