Published inNVIDIA MerlinSolving the Cold-Start Problem using Two-Tower Neural Networks for NVIDIA’s E-Mail Recommender…There are many great resources and examples for machine learning. But they are often based on public (and sometimes even toy) datasets. The…Jan 11, 20231Jan 11, 20231
Published inNVIDIA MerlinData Cleaning and Preprocessing for Recommender Systems based on NVIDIA’s Use CaseHave you ever heard that 80% of a data scientist’s work is data cleaning? That is probably correct. Data cleaning was really important for…Dec 7, 2022Dec 7, 2022
Published inNVIDIA MerlinHow to build a recommender system: A real Use Case to personalize E-Mail campaignsWe share our approach, challenges and learnings for developing a recommender system to personalize the E-Mail marketing campaignsNov 2, 20221Nov 2, 20221
Published inNVIDIA MerlinOptimizing Meituan’s Machine Learning Platform: An Interview with Jun HuangBy Sheng Luo and Benedikt SchiffererSep 29, 2021Sep 29, 2021
Published inNVIDIA MerlinWinning the RecSys2021 Challenge by a Diverse Set of XGBoost and Neural Network ModelsLearn about the winning solution of the RecSys2021 Challenge and how to accelerate inference with GPUs.Jul 22, 2021Jul 22, 2021
Published inNVIDIA MerlinLearn how Spotify, Walmart, Tencent and Postmates are scaling and accelerating their recommender…By Benedikt Schifferer, Ronay Ak and Even OldridgeApr 6, 2021Apr 6, 2021
Published inNVIDIA MerlinA New API for NVTabular and Inference support are coming with Merlin’s 0.4 releaseBy Benedikt Schifferer and Even OldridgeMar 10, 2021Mar 10, 2021
Published inNVIDIA MerlinFaster GPU-based Feature Engineering and Tabular Deep Learning Training with NVTabular on Kaggle.comBy Benedikt Schifferer and Even OldridgeJan 26, 2021Jan 26, 2021
Published inRAPIDS AIWinning Solution of RecSys2020 Challenge: GPU Accelerated Feature Engineering and Training for…Our GPU-optimized pipeline enabled us to quickly iterate and run many experiments in a short time, giving us a competitive advantage to…Sep 23, 20201Sep 23, 20201
