Kaggle Grandmasters of NVIDIA (KGMoN)

Meet the Kaggle Grandmasters of NVIDIA, and learn how they use NVIDIA accelerated data science to build winning recommender systems, predict degradation rates in RNA molecules, identify melanoma in medical imaging, and more.

Meet the KGMoN Team

Ahmet Erdem

Ahmet Erdem

Senior Data Scientist at NVIDIA

Chris Deott

Chris Deott

Senior Data Scientist at NVIDIA

Christof Henkel

Christof Henkel

Data Scientist at NVIDIA

Gilberto Titericz

Gilberto Titericz

Data Scientist at NVIDIA

Jean-Francois Puget

Jean-Francois Puget

Distinguished Engineer at NVIDIA

Jiwei Liu

Jiwei Liu

Senior Data Scientist at NVIDIA

Kazuki Onodera

Kazuki Onodera

Senior Data Scientist at NVIDIA

Explore the KGMoN Team’s Recent Competitions

The Recommender Systems Challenge

JUNE 2021

The RecSys Challenge

The NVIDIA Merlin and KGMON team earned 1st place in the RecSys Challenge 2021 by effectively predicting the probability of user engagement within a dynamic environment and providing fair recommendations on a multi-million point dataset.

Booking.com Destination Recommendation Challenge

MARCH 2021

Booking.com Web Search and Data Mining (WSDM) WebTour 2021 Challenge


In this recommendation system challenge, the goal was to use a dataset based on millions of real anonymized accommodation reservations to come up with a strategy for making the best recommendation for their next destination, all in real-time.

COVID-19 mRNA Vaccine Degradation Prediction Competition

OCTOBER 2020

OpenVaccine: COVID-19 mRNA Vaccine Degradation Prediction


In this competition, teams were charged with developing machine learning models and designing rules for RNA degradation. The models needed to predict likely degradation rates at each base of an RNA molecule, trained on a subset of an Eterna dataset comprising over 3000 RNA molecules (which span a panoply of sequences and structures) and their degradation rates at each position.

Google Landmark Recognition 2020

SEPTEMBER 2020

Google Landmark Recognition 2020


In this landmark recognition challenge, the team had to build models that recognize the correct landmark (if any) in a dataset of complicated test images. This is easier said than done, given landmark recognition contains a much larger number of classes. For example, there were more than 81,000 classes in this competition.

SIIM-ISIC Melanoma Classification

AUGUST 2020

SIIM-ISIC Melanoma Classificatione


In this competition, the team had to create ML models to identify skin lesions from patients’ images and determine which images are most likely to represent a melanoma. The winning ML model was able to identify melanoma earlier and more accurately than the average dermatologist.

Grandmaster Series

The Grandmaster Series is a monthly educational video series for data scientists. In each episode, you'll hear from the world's leading experts in data science as they share their insights, best practices, and key learnings from a recent competition. Tune in and learn how you can apply their learnings to your own data science challenges.

Sign Up To Receive Data Science News