article thumbnail

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

AWS Machine Learning

Models were trained and cross-validated on the 2018, 2019, and 2020 seasons and tested on the 2021 season. Furthermore, we looked at the probability of a touchdown and probability plots to evaluate calibration. For more information on how to use GluonTS SBP, see the following demo notebook. k10 Baseline 0 4.074 9.62

article thumbnail

Face-off Probability, part of NHL Edge IQ: Predicting face-off winners in real time during televised games

AWS Machine Learning

With PPT data from the 2020-2021 season, we built a model to predict the likelihood that a face-off is occurring at a specified location given the average distance of each team to the location and the velocities of the players. At the end, we found that the LightGBM model worked best with well-calibrated accuracy metrics.

article thumbnail

LiDAR 3D point cloud labeling with Velodyne LiDAR sensor in Amazon SageMaker Ground Truth

AWS Machine Learning

LiDAR is a key enabling technology in growing autonomous markets, such as robotics, industrial, infrastructure, and automotive. With a combination of optimal power and high performance, this sensor provides distance and calibrated reflectivity measurements at all rotational angles. LiDAR vehicle calibration. The LiDAR dataset.