{
  "id": 330987,
  "title": "Temporal features in the dataset",
  "url": "/competitions/amex-default-prediction/discussion/330987",
  "author_name": "",
  "post_date": "2022-06-15T08:33:56.418022300Z",
  "votes": 41,
  "comment_count": 2,
  "views": 0,
  "content": "<p>The key to solving this competition is to exploit the temporal component of the dataset. I have spent some time on this and there a couple of insights I'd like to share:</p>\n<p><a href=\"https://www.kaggle.com/code/raddar/learning-to-rank-time-related-features/\" target=\"_blank\">https://www.kaggle.com/code/raddar/learning-to-rank-time-related-features/</a></p>\n<p>I think learning to rank models are often underutilized and have huge potential in this competition!</p>",
  "messages": [
    {
      "id": "1821070",
      "postDate": "06/15/2022 08:33:56",
      "content": "<p>The key to solving this competition is to exploit the temporal component of the dataset. I have spent some time on this and there a couple of insights I'd like to share:</p>\n<p><a href=\"https://www.kaggle.com/code/raddar/learning-to-rank-time-related-features/\" target=\"_blank\">https://www.kaggle.com/code/raddar/learning-to-rank-time-related-features/</a></p>\n<p>I think learning to rank models are often underutilized and have huge potential in this competition!</p>",
      "rawMarkdown": "The key to solving this competition is to exploit the temporal component of the dataset. I have spent some time on this and there a couple of insights I'd like to share:\n\nhttps://www.kaggle.com/code/raddar/learning-to-rank-time-related-features/\n\nI think learning to rank models are often underutilized and have huge potential in this competition!",
      "votes": null
    },
    {
      "id": "1821113",
      "postDate": "06/15/2022 09:00:50",
      "content": "<p>Thank you for sharing!<br>\nThe rank model was widely used in <a href=\"https://www.kaggle.com/competitions/h-and-m-personalized-fashion-recommendations/discussion?sort=recent-comments\" target=\"_blank\">H&amp;M Personalized Fashion Recommendations</a>.</p>",
      "rawMarkdown": "Thank you for sharing!\nThe rank model was widely used in [H&M Personalized Fashion Recommendations](https://www.kaggle.com/competitions/h-and-m-personalized-fashion-recommendations/discussion?sort=recent-comments).",
      "votes": null
    },
    {
      "id": "1822334",
      "postDate": "06/16/2022 09:06:05",
      "content": "<p>AUC metric hints at the usefulness of ranking models. Thanks for this, my man, raddar.</p>",
      "rawMarkdown": "AUC metric hints at the usefulness of ranking models. Thanks for this, my man, raddar.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1821113,
      "author_name": "zakopur0",
      "author_url": "",
      "post_date": "06/15/2022 09:00:50",
      "content": "<p>Thank you for sharing!<br>\nThe rank model was widely used in <a href=\"https://www.kaggle.com/competitions/h-and-m-personalized-fashion-recommendations/discussion?sort=recent-comments\" target=\"_blank\">H&amp;M Personalized Fashion Recommendations</a>.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1822334,
      "author_name": "donotfutureskip",
      "author_url": "",
      "post_date": "06/16/2022 09:06:05",
      "content": "<p>AUC metric hints at the usefulness of ranking models. Thanks for this, my man, raddar.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1821070": "The key to solving this competition is to exploit the temporal component of the dataset. I have spent some time on this and there a couple of insights I'd like to share:\n\nhttps://www.kaggle.com/code/raddar/learning-to-rank-time-related-features/\n\nI think learning to rank models are often underutilized and have huge potential in this competition!",
    "1821113": "Thank you for sharing!\nThe rank model was widely used in [H&M Personalized Fashion Recommendations](https://www.kaggle.com/competitions/h-and-m-personalized-fashion-recommendations/discussion?sort=recent-comments).",
    "1822334": "AUC metric hints at the usefulness of ranking models. Thanks for this, my man, raddar."
  },
  "source": "meta"
}