Boosted Trees & Deep Neural Networks for Better Recommender Systems – Grandmaster Series, E6

In episode six of the Grandmaster Series, learn how participating members of the Kaggle Grandmasters of NVIDIA (KGMON) used GPU-accelerated boosted trees and deep neural networks to build the winning recommender system in the ACM RecSys Challenge, hosted by Twitter. In this recommendation system challenge, the goal was to predict the probability for different types of engagement (Like, Reply, Retweet, and Retweet with Comment) of a target user for a set of tweets, based on heterogeneous input data. Watch the video to see their winning solution. Subscribe to our Youtube channel to be notified when we publish a new Grandmaster Series episode. If you have any questions during the video, you can submit them through chat. We will try to provide answers throughout and at the end of the episode. Video Chapters: 00:00 – Intro to Episode Six 03:20 – ACM RecSys Challenge Overview 19:10 – Neural Network Models 31:34 – Target Encoding & XGBoost Models 57:14 – Stacking