{
  "id": 299632,
  "title": "Retraining after submission",
  "url": "/competitions/g-research-crypto-forecasting/discussion/299632",
  "author_name": "",
  "post_date": "2022-01-09T08:08:30.395206300Z",
  "votes": 5,
  "comment_count": 1,
  "views": 0,
  "content": "<p>I believe to have understood that post-submission deadline, the models will be retrained by GResearch (I assume simply exchanging the train.csv set and rerunning the notebooks) using data from the submission period before starting the evaluation. Anything you have thought about there to avoid errors during that process?</p>\n<p>The only thing I can think about is to use the whole train.csv for training of the model and avoid any sort of splitting of train.csv in the submitted notebook.</p>",
  "messages": [
    {
      "id": "1643235",
      "postDate": "01/09/2022 08:08:30",
      "content": "<p>I believe to have understood that post-submission deadline, the models will be retrained by GResearch (I assume simply exchanging the train.csv set and rerunning the notebooks) using data from the submission period before starting the evaluation. Anything you have thought about there to avoid errors during that process?</p>\n<p>The only thing I can think about is to use the whole train.csv for training of the model and avoid any sort of splitting of train.csv in the submitted notebook.</p>",
      "rawMarkdown": "I believe to have understood that post-submission deadline, the models will be retrained by GResearch (I assume simply exchanging the train.csv set and rerunning the notebooks) using data from the submission period before starting the evaluation. Anything you have thought about there to avoid errors during that process?\n\nThe only thing I can think about is to use the whole train.csv for training of the model and avoid any sort of splitting of train.csv in the submitted notebook.",
      "votes": null
    },
    {
      "id": "1645927",
      "postDate": "01/11/2022 10:59:21",
      "content": "<p>I don't know if I understand your question correctly. 😂😂</p>\n<p>Generally speaking, once the model works fine for the training set provided, Kaggle can also run successfully after changing the training set (because the features of train.csv are guaranteed to be consistent).</p>\n<p>Please forgive me if I understand incorrectly!</p>",
      "rawMarkdown": "I don't know if I understand your question correctly. 😂😂\n\nGenerally speaking, once the model works fine for the training set provided, Kaggle can also run successfully after changing the training set (because the features of train.csv are guaranteed to be consistent).\n\nPlease forgive me if I understand incorrectly!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1645927,
      "author_name": "",
      "author_url": "",
      "post_date": "01/11/2022 10:59:21",
      "content": "<p>I don't know if I understand your question correctly. 😂😂</p>\n<p>Generally speaking, once the model works fine for the training set provided, Kaggle can also run successfully after changing the training set (because the features of train.csv are guaranteed to be consistent).</p>\n<p>Please forgive me if I understand incorrectly!</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1643235": "I believe to have understood that post-submission deadline, the models will be retrained by GResearch (I assume simply exchanging the train.csv set and rerunning the notebooks) using data from the submission period before starting the evaluation. Anything you have thought about there to avoid errors during that process?\n\nThe only thing I can think about is to use the whole train.csv for training of the model and avoid any sort of splitting of train.csv in the submitted notebook.",
    "1645927": "I don't know if I understand your question correctly. 😂😂\n\nGenerally speaking, once the model works fine for the training set provided, Kaggle can also run successfully after changing the training set (because the features of train.csv are guaranteed to be consistent).\n\nPlease forgive me if I understand incorrectly!"
  },
  "source": "meta"
}