{
  "id": 384636,
  "title": "3rd Place Code ",
  "url": "/competitions/otto-recommender-system/discussion/384636",
  "author_name": "Theo Viel",
  "post_date": "2023-02-08T18:29:56.741000",
  "votes": 28,
  "comment_count": 4,
  "views": 0,
  "content": "<p>Hey folks,</p>\n<p>Now that the LB is finalized, I've released the code to reproduce my part of the 3rd place solution. </p>\n<blockquote>\n  <p><a href=\"https://github.com/TheoViel/kaggle_otto_rs\" target=\"_blank\">https://github.com/TheoViel/kaggle_otto_rs</a></p>\n</blockquote>\n<p>It also contains <a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a>'s code to generate covisitation matrices &amp; candidates, <a href=\"https://www.kaggle.com/benediktschifferer\" target=\"_blank\">@benediktschifferer</a>'s code for Word2vec embeddings, and <a href=\"https://www.kaggle.com/titericz\" target=\"_blank\">@titericz</a>'s code for matrix factorization. Thanks again to them for the great competiton. </p>\n<p>I hope it can be useful to anyone, it's time to move on to other things !<br>\nLet me know if you try to run the full pipeline, I may have introduced some issues while refactoring everything.</p>",
  "messages": [
    {
      "id": 2135606,
      "postDate": "2023-02-08T18:29:56.740Z",
      "content": "<p>Hey folks,</p>\n<p>Now that the LB is finalized, I've released the code to reproduce my part of the 3rd place solution. </p>\n<blockquote>\n  <p><a href=\"https://github.com/TheoViel/kaggle_otto_rs\" target=\"_blank\">https://github.com/TheoViel/kaggle_otto_rs</a></p>\n</blockquote>\n<p>It also contains <a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a>'s code to generate covisitation matrices &amp; candidates, <a href=\"https://www.kaggle.com/benediktschifferer\" target=\"_blank\">@benediktschifferer</a>'s code for Word2vec embeddings, and <a href=\"https://www.kaggle.com/titericz\" target=\"_blank\">@titericz</a>'s code for matrix factorization. Thanks again to them for the great competiton. </p>\n<p>I hope it can be useful to anyone, it's time to move on to other things !<br>\nLet me know if you try to run the full pipeline, I may have introduced some issues while refactoring everything.</p>",
      "rawMarkdown": "Hey folks,\n\nNow that the LB is finalized, I've released the code to reproduce my part of the 3rd place solution. \n > https://github.com/TheoViel/kaggle_otto_rs\n\nIt also contains @cdeotte's code to generate covisitation matrices & candidates, @benediktschifferer's code for Word2vec embeddings, and @titericz's code for matrix factorization. Thanks again to them for the great competiton. \n\nI hope it can be useful to anyone, it's time to move on to other things !\nLet me know if you try to run the full pipeline, I may have introduced some issues while refactoring everything.",
      "votes": 27
    },
    {
      "id": 2186715,
      "postDate": "2023-03-18T03:37:14.507Z",
      "content": "<p>thx, really learn a lot from that</p>",
      "rawMarkdown": "thx, really learn a lot from that"
    },
    {
      "id": 2139631,
      "postDate": "2023-02-10T23:47:35.437Z",
      "content": "<p>Hello, <a href=\"https://www.kaggle.com/theoviel\" target=\"_blank\">@theoviel</a> thanks for sharing your solution, looking forward to learning from your code.</p>",
      "rawMarkdown": "Hello, @theoviel thanks for sharing your solution, looking forward to learning from your code."
    },
    {
      "id": 2165143,
      "postDate": "2023-03-02T02:49:07.013Z",
      "rawMarkdown": "",
      "isDeleted": true
    },
    {
      "id": 2165445,
      "postDate": "2023-03-02T08:08:29.647Z",
      "content": "<p>Thank you so much for sharing!</p>",
      "rawMarkdown": "Thank you so much for sharing!"
    }
  ],
  "comments": [
    {
      "id": 2186715,
      "author_name": "JoeJoeW",
      "author_url": "",
      "post_date": "2023-03-18T03:37:14.507000",
      "content": "<p>thx, really learn a lot from that</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 2139631,
      "author_name": "C4rl05/V",
      "author_url": "",
      "post_date": "2023-02-10T23:47:35.437000",
      "content": "<p>Hello, <a href=\"https://www.kaggle.com/theoviel\" target=\"_blank\">@theoviel</a> thanks for sharing your solution, looking forward to learning from your code.</p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 2165143,
      "author_name": "",
      "author_url": "",
      "post_date": "2023-03-02T02:49:07.013000",
      "content": "",
      "votes": 0,
      "replies": []
    },
    {
      "id": 2165445,
      "author_name": "Ngọc Uyên Nguyễn",
      "author_url": "",
      "post_date": "2023-03-02T08:08:29.647000",
      "content": "<p>Thank you so much for sharing!</p>",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2135606": "Hey folks,\n\nNow that the LB is finalized, I've released the code to reproduce my part of the 3rd place solution. \n > https://github.com/TheoViel/kaggle_otto_rs\n\nIt also contains @cdeotte's code to generate covisitation matrices & candidates, @benediktschifferer's code for Word2vec embeddings, and @titericz's code for matrix factorization. Thanks again to them for the great competiton. \n\nI hope it can be useful to anyone, it's time to move on to other things !\nLet me know if you try to run the full pipeline, I may have introduced some issues while refactoring everything.",
    "2186715": "thx, really learn a lot from that",
    "2139631": "Hello, @theoviel thanks for sharing your solution, looking forward to learning from your code.",
    "2165143": "",
    "2165445": "Thank you so much for sharing!"
  }
}