{
  "id": 364639,
  "title": "Papers and Winning Code From NVidia Recommender Systems Team",
  "url": "/competitions/otto-recommender-system/discussion/364639",
  "author_name": "Gaju Ahmed",
  "post_date": "2022-11-07T16:29:34.502000",
  "votes": 18,
  "comment_count": 0,
  "views": 0,
  "content": "<ul>\n<li><p><a href=\"https://www.youtube.com/watch?v=bHuww-l_Sq0&amp;list=PL5B692fm6--uXbxtmPJz5nu3Xmc1JUm3F&amp;index=1\">How to Build a Winning Deep Learning Recommender System </a> Grandmaster Series By Nvidia Part-1</p></li>\n<li><p><a href=\"https://www.youtube.com/watch?v=a9hmgAtDhkg&amp;list=PL5B692fm6--uXbxtmPJz5nu3Xmc1JUm3F&amp;index=6\">Boosted Trees &amp; Deep Neural Networks for Better Recommender Systems E-6</a> Grandmaster Series By Nvidia Part-2</p></li>\n<li><p><strong><a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/WSDM_WebTour2021_Challenge\">Deep Learning to Win the Booking.com WSDM WebTour21 Challenge on Sequential Recommendations</a></strong><br>\n<a href=\"https://postimg.cc/G9Q13sBc\" target=\"_blank\"><img src=\"https://i.postimg.cc/Gh03QFds/p1.png\" alt=\"p1.png\"></a></p></li>\n<li><p><a href=\"https://github.com/NVIDIA-Merlin/competitions/blob/main/RecSys2022_Challenge/A-Diverse-Models-Ensemble-for-Fashion-Session-Based-Recommendation.pdf\"><strong>A-Diverse-Models-Ensemble-for-Fashion-Session-Based-Recommendation</strong></a><br>\n<a href=\"https://postimg.cc/py3JF9bj\" target=\"_blank\"><img src=\"https://i.postimg.cc/xT1xBH66/p1.png\" alt=\"p1.png\"></a></p></li>\n<li><p><a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/RecSys2021_Challenge\"><strong>GPU Accelerated Boosted Trees and Deep Neural Networks for Better Recommender Systems</strong></a><br>\n<a href=\"https://postimg.cc/V0z1Gf2W\" target=\"_blank\"><img src=\"https://i.postimg.cc/zvgBf3j6/p1.png\" alt=\"p1.png\"></a></p></li>\n<li><p><strong><a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/SIGIR_eCommerce_Challenge_2021/task2_purchase_prediction\">E-Commerce Workshop Data Challenge - Purchase Intent Prediction Task</a></strong><br>\n<a href=\"https://postimg.cc/gXtr1Bb7\" target=\"_blank\"><img src=\"https://i.postimg.cc/yxs9gwQ7/p1.png\" alt=\"p1.png\"></a></p></li>\n<li><p><strong><a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/RecSys2020_Challenge\">GPU Accelerated Feature Engineering and Training for Recommender Systems</a></strong><br>\nThis repository contains the code of the winning solution of the RecSys2020 Challenge - GPU Accelerated Feature Engineering and Training for Recommender Systems - achieving the highest score in seven of the eight metrics used to calculate the final leaderboard position. In addition to the original end-2-end source code, the repository demonstrates the 25x speed-up by comparing highly optimized CPU (dask and pandas) with highly optimized GPU accelerated versions (dask and cuDF).</p></li>\n</ul>",
  "messages": [
    {
      "id": 2020611,
      "postDate": "2022-11-07T16:29:34.503Z",
      "content": "<ul>\n<li><p><a href=\"https://www.youtube.com/watch?v=bHuww-l_Sq0&amp;list=PL5B692fm6--uXbxtmPJz5nu3Xmc1JUm3F&amp;index=1\">How to Build a Winning Deep Learning Recommender System </a> Grandmaster Series By Nvidia Part-1</p></li>\n<li><p><a href=\"https://www.youtube.com/watch?v=a9hmgAtDhkg&amp;list=PL5B692fm6--uXbxtmPJz5nu3Xmc1JUm3F&amp;index=6\">Boosted Trees &amp; Deep Neural Networks for Better Recommender Systems E-6</a> Grandmaster Series By Nvidia Part-2</p></li>\n<li><p><strong><a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/WSDM_WebTour2021_Challenge\">Deep Learning to Win the Booking.com WSDM WebTour21 Challenge on Sequential Recommendations</a></strong><br>\n<a href=\"https://postimg.cc/G9Q13sBc\" target=\"_blank\"><img src=\"https://i.postimg.cc/Gh03QFds/p1.png\" alt=\"p1.png\"></a></p></li>\n<li><p><a href=\"https://github.com/NVIDIA-Merlin/competitions/blob/main/RecSys2022_Challenge/A-Diverse-Models-Ensemble-for-Fashion-Session-Based-Recommendation.pdf\"><strong>A-Diverse-Models-Ensemble-for-Fashion-Session-Based-Recommendation</strong></a><br>\n<a href=\"https://postimg.cc/py3JF9bj\" target=\"_blank\"><img src=\"https://i.postimg.cc/xT1xBH66/p1.png\" alt=\"p1.png\"></a></p></li>\n<li><p><a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/RecSys2021_Challenge\"><strong>GPU Accelerated Boosted Trees and Deep Neural Networks for Better Recommender Systems</strong></a><br>\n<a href=\"https://postimg.cc/V0z1Gf2W\" target=\"_blank\"><img src=\"https://i.postimg.cc/zvgBf3j6/p1.png\" alt=\"p1.png\"></a></p></li>\n<li><p><strong><a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/SIGIR_eCommerce_Challenge_2021/task2_purchase_prediction\">E-Commerce Workshop Data Challenge - Purchase Intent Prediction Task</a></strong><br>\n<a href=\"https://postimg.cc/gXtr1Bb7\" target=\"_blank\"><img src=\"https://i.postimg.cc/yxs9gwQ7/p1.png\" alt=\"p1.png\"></a></p></li>\n<li><p><strong><a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/RecSys2020_Challenge\">GPU Accelerated Feature Engineering and Training for Recommender Systems</a></strong><br>\nThis repository contains the code of the winning solution of the RecSys2020 Challenge - GPU Accelerated Feature Engineering and Training for Recommender Systems - achieving the highest score in seven of the eight metrics used to calculate the final leaderboard position. In addition to the original end-2-end source code, the repository demonstrates the 25x speed-up by comparing highly optimized CPU (dask and pandas) with highly optimized GPU accelerated versions (dask and cuDF).</p></li>\n</ul>",
      "rawMarkdown": "- <a href=\"https://www.youtube.com/watch?v=bHuww-l_Sq0&list=PL5B692fm6--uXbxtmPJz5nu3Xmc1JUm3F&index=1\">How to Build a Winning Deep Learning Recommender System </a> Grandmaster Series By Nvidia Part-1\n- <a href=\"https://www.youtube.com/watch?v=a9hmgAtDhkg&list=PL5B692fm6--uXbxtmPJz5nu3Xmc1JUm3F&index=6\">Boosted Trees & Deep Neural Networks for Better Recommender Systems E-6</a> Grandmaster Series By Nvidia Part-2\n\n- **<a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/WSDM_WebTour2021_Challenge\">Deep Learning to Win the Booking.com WSDM WebTour21 Challenge on Sequential Recommendations</a>**\n[![p1.png](https://i.postimg.cc/Gh03QFds/p1.png)](https://postimg.cc/G9Q13sBc)\n\n- <a href=\"https://github.com/NVIDIA-Merlin/competitions/blob/main/RecSys2022_Challenge/A-Diverse-Models-Ensemble-for-Fashion-Session-Based-Recommendation.pdf\">**A-Diverse-Models-Ensemble-for-Fashion-Session-Based-Recommendation**</a>\n[![p1.png](https://i.postimg.cc/xT1xBH66/p1.png)](https://postimg.cc/py3JF9bj)\n\n- <a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/RecSys2021_Challenge\">**GPU Accelerated Boosted Trees and Deep Neural Networks for Better Recommender Systems**</a>\n[![p1.png](https://i.postimg.cc/zvgBf3j6/p1.png)](https://postimg.cc/V0z1Gf2W)\n\n- **<a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/SIGIR_eCommerce_Challenge_2021/task2_purchase_prediction\">E-Commerce Workshop Data Challenge - Purchase Intent Prediction Task</a>**\n[![p1.png](https://i.postimg.cc/yxs9gwQ7/p1.png)](https://postimg.cc/gXtr1Bb7)\n\n- **<a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/RecSys2020_Challenge\">GPU Accelerated Feature Engineering and Training for Recommender Systems</a>**\nThis repository contains the code of the winning solution of the RecSys2020 Challenge - GPU Accelerated Feature Engineering and Training for Recommender Systems - achieving the highest score in seven of the eight metrics used to calculate the final leaderboard position. In addition to the original end-2-end source code, the repository demonstrates the 25x speed-up by comparing highly optimized CPU (dask and pandas) with highly optimized GPU accelerated versions (dask and cuDF).",
      "votes": 18
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2020611": "- <a href=\"https://www.youtube.com/watch?v=bHuww-l_Sq0&list=PL5B692fm6--uXbxtmPJz5nu3Xmc1JUm3F&index=1\">How to Build a Winning Deep Learning Recommender System </a> Grandmaster Series By Nvidia Part-1\n- <a href=\"https://www.youtube.com/watch?v=a9hmgAtDhkg&list=PL5B692fm6--uXbxtmPJz5nu3Xmc1JUm3F&index=6\">Boosted Trees & Deep Neural Networks for Better Recommender Systems E-6</a> Grandmaster Series By Nvidia Part-2\n\n- **<a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/WSDM_WebTour2021_Challenge\">Deep Learning to Win the Booking.com WSDM WebTour21 Challenge on Sequential Recommendations</a>**\n[![p1.png](https://i.postimg.cc/Gh03QFds/p1.png)](https://postimg.cc/G9Q13sBc)\n\n- <a href=\"https://github.com/NVIDIA-Merlin/competitions/blob/main/RecSys2022_Challenge/A-Diverse-Models-Ensemble-for-Fashion-Session-Based-Recommendation.pdf\">**A-Diverse-Models-Ensemble-for-Fashion-Session-Based-Recommendation**</a>\n[![p1.png](https://i.postimg.cc/xT1xBH66/p1.png)](https://postimg.cc/py3JF9bj)\n\n- <a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/RecSys2021_Challenge\">**GPU Accelerated Boosted Trees and Deep Neural Networks for Better Recommender Systems**</a>\n[![p1.png](https://i.postimg.cc/zvgBf3j6/p1.png)](https://postimg.cc/V0z1Gf2W)\n\n- **<a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/SIGIR_eCommerce_Challenge_2021/task2_purchase_prediction\">E-Commerce Workshop Data Challenge - Purchase Intent Prediction Task</a>**\n[![p1.png](https://i.postimg.cc/yxs9gwQ7/p1.png)](https://postimg.cc/gXtr1Bb7)\n\n- **<a href=\"https://github.com/NVIDIA-Merlin/competitions/tree/main/RecSys2020_Challenge\">GPU Accelerated Feature Engineering and Training for Recommender Systems</a>**\nThis repository contains the code of the winning solution of the RecSys2020 Challenge - GPU Accelerated Feature Engineering and Training for Recommender Systems - achieving the highest score in seven of the eight metrics used to calculate the final leaderboard position. In addition to the original end-2-end source code, the repository demonstrates the 25x speed-up by comparing highly optimized CPU (dask and pandas) with highly optimized GPU accelerated versions (dask and cuDF)."
  }
}