{
  "id": 506319,
  "title": "Which features were transformed in test dataset after the update?",
  "url": "/competitions/home-credit-credit-risk-model-stability/discussion/506319",
  "author_name": "ano",
  "post_date": "2024-05-21T11:52:59.934000",
  "votes": 3,
  "comment_count": 0,
  "views": 0,
  "content": "<p>I understand that some of (or all of?) the date-related features were transformed in test dataset (but not in train dataset) and should not be used in training (You may use, but I think they are meaningless).<br>\n<a href=\"https://www.kaggle.com/competitions/home-credit-credit-risk-model-stability/discussion/482474\" target=\"_blank\">https://www.kaggle.com/competitions/home-credit-credit-risk-model-stability/discussion/482474</a></p>\n<p>What is not clear to me is that the specific features that were transformed. I have confirmed, after submitting several times, that some of the features whose name ends with \"D\" were transformed, but were the date-related features whose name ends with \"T\" also transformed as well?</p>",
  "messages": [
    {
      "id": 2827329,
      "postDate": "2024-05-21T11:52:59.933Z",
      "content": "<p>I understand that some of (or all of?) the date-related features were transformed in test dataset (but not in train dataset) and should not be used in training (You may use, but I think they are meaningless).<br>\n<a href=\"https://www.kaggle.com/competitions/home-credit-credit-risk-model-stability/discussion/482474\" target=\"_blank\">https://www.kaggle.com/competitions/home-credit-credit-risk-model-stability/discussion/482474</a></p>\n<p>What is not clear to me is that the specific features that were transformed. I have confirmed, after submitting several times, that some of the features whose name ends with \"D\" were transformed, but were the date-related features whose name ends with \"T\" also transformed as well?</p>",
      "rawMarkdown": "I understand that some of (or all of?) the date-related features were transformed in test dataset (but not in train dataset) and should not be used in training (You may use, but I think they are meaningless).\nhttps://www.kaggle.com/competitions/home-credit-credit-risk-model-stability/discussion/482474\n\nWhat is not clear to me is that the specific features that were transformed. I have confirmed, after submitting several times, that some of the features whose name ends with \"D\" were transformed, but were the date-related features whose name ends with \"T\" also transformed as well?",
      "votes": 3
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2827329": "I understand that some of (or all of?) the date-related features were transformed in test dataset (but not in train dataset) and should not be used in training (You may use, but I think they are meaningless).\nhttps://www.kaggle.com/competitions/home-credit-credit-risk-model-stability/discussion/482474\n\nWhat is not clear to me is that the specific features that were transformed. I have confirmed, after submitting several times, that some of the features whose name ends with \"D\" were transformed, but were the date-related features whose name ends with \"T\" also transformed as well?"
  }
}