2020, Clean Data and Cross Validation

Predict football punt and kickoff return yards with fat-tailed distribution using GluonTS

Flipboard

FEBRUARY 2, 2023

Models were trained and cross-validated on the 2018, 2019, and 2020 seasons and tested on the 2021 season. To avoid leakage during cross-validation, we grouped all plays from the same game into the same fold. For more information on how to use GluonTS SBP, see the following demo notebook.

Cross Validation

Cross Validation ML ML Machine Learning

Identifying defense coverage schemes in NFL’s Next Gen Stats

AWS Machine Learning Blog

FEBRUARY 10, 2023

Feature engineering Game tracking data is captured at 10 frames per second, including the player location, speed, acceleration, and orientation. Quantitative evaluation We utilize 2018–2020 season data for model training and validation, and 2021 season data for model evaluation.

ML ML Machine Learning Machine Learning

Data Science Current

Predict football punt and kickoff return yards with fat-tailed distribution using GluonTS

Identifying defense coverage schemes in NFL’s Next Gen Stats

Webinars

Stay Connected