694: CatBoost: Powerful, efficient ML for large tabular datasets

Modeling tabular data and spreadsheets doesn’t have to be tedious with CatBoost’s open-source tree-boosting algorithm. CatBoost does what it says on the tin, blending categories with boosting that allows you to train your models faster and handle large datasets for ML tasks across multiple GPUs. In this week’s Five-Minute Friday, host Jon Krohn gets to grips with the technical components of CatBoost that give it the speed and accuracy so acclaimed by its users.

Additional materials: www.superdatascience.com/694

Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.