Sequential Ice Hockey Events Generation using Generative Adversarial Network

Abstract

We have generated events and coordinates that lead to a hockey goal in this project. Swedish Hockey League data from season 2020-21 for twenty matches provided by Sportlogiq were used that contain event data of those matches. We used TimeGAN to generate event data. TimeGAN learns the distribution of the original time-series data and creates a synthetic version of it. After that, we showed which events led to a goal from the synthetic data. We used principal component analysis (PCA) plots to show the original and synthetic data distributions as a qualitative evaluation. Also, we have used a sequence prediction model to test the synthetic data quantitatively. We compared the synthetic data quality with another two GAN models.