{
  "id": 580307,
  "title": "Masked Test Data",
  "url": "/competitions/drw-crypto-market-prediction/discussion/580307",
  "author_name": "",
  "post_date": "2025-05-23T18:12:38.614103100Z",
  "votes": null,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Since the test data is masked and jumbled, any temporal patterns in the training data say by window approach won't work right?<br>\nPlease correct me if I'm wrong</p>",
  "messages": [
    {
      "id": "3208121",
      "postDate": "05/23/2025 18:12:38",
      "content": "<p>Since the test data is masked and jumbled, any temporal patterns in the training data say by window approach won't work right?<br>\nPlease correct me if I'm wrong</p>",
      "rawMarkdown": "Since the test data is masked and jumbled, any temporal patterns in the training data say by window approach won't work right?\nPlease correct me if I'm wrong",
      "votes": null
    },
    {
      "id": "3208473",
      "postDate": "05/24/2025 07:36:39",
      "content": "<p>You are right. You should not use the ordering of the training set nor when evaluating on the validation set.</p>",
      "rawMarkdown": "You are right. You should not use the ordering of the training set nor when evaluating on the validation set.",
      "votes": null
    },
    {
      "id": "3208516",
      "postDate": "05/24/2025 09:16:03",
      "content": "<p>yes, temporal patterns learned from the training data won't be usable on the test data if its time order is  shuffled 😪</p>",
      "rawMarkdown": "yes, temporal patterns learned from the training data won't be usable on the test data if its time order is  shuffled 😪",
      "votes": null
    },
    {
      "id": "3236568",
      "postDate": "06/30/2025 12:44:16",
      "content": "<p>yes you are right</p>",
      "rawMarkdown": "yes you are right",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3208473,
      "author_name": "quentinadatte1307",
      "author_url": "",
      "post_date": "05/24/2025 07:36:39",
      "content": "<p>You are right. You should not use the ordering of the training set nor when evaluating on the validation set.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 3208516,
      "author_name": "michalinahulak",
      "author_url": "",
      "post_date": "05/24/2025 09:16:03",
      "content": "<p>yes, temporal patterns learned from the training data won't be usable on the test data if its time order is  shuffled 😪</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 3236568,
      "author_name": "twochar24",
      "author_url": "",
      "post_date": "06/30/2025 12:44:16",
      "content": "<p>yes you are right</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "3208121": "Since the test data is masked and jumbled, any temporal patterns in the training data say by window approach won't work right?\nPlease correct me if I'm wrong",
    "3208473": "You are right. You should not use the ordering of the training set nor when evaluating on the validation set.",
    "3208516": "yes, temporal patterns learned from the training data won't be usable on the test data if its time order is  shuffled 😪",
    "3236568": "yes you are right"
  },
  "source": "meta"
}