{
  "id": 202076,
  "title": "Predicting for New user Id in Test",
  "url": "/competitions/riiid-test-answer-prediction/discussion/202076",
  "author_name": "",
  "post_date": "2020-12-08T07:24:59.907663400Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Please pardon me if this is answered some where.<br>\nCan some one help me  in knowing how we can predict for the user ids not in whole train set. </p>\n<p><a href=\"https://www.kaggle.com/mpware/sakt-fork?scriptVersionId=48197140\" target=\"_blank\">https://www.kaggle.com/mpware/sakt-fork?scriptVersionId=48197140</a></p>\n<p>Inference in this kernel relies over only the Users present in Valid Group but what if the user not there how we will predict for that user id</p>",
  "messages": [
    {
      "id": "1105771",
      "postDate": "12/08/2020 07:24:59",
      "content": "<p>Please pardon me if this is answered some where.<br>\nCan some one help me  in knowing how we can predict for the user ids not in whole train set. </p>\n<p><a href=\"https://www.kaggle.com/mpware/sakt-fork?scriptVersionId=48197140\" target=\"_blank\">https://www.kaggle.com/mpware/sakt-fork?scriptVersionId=48197140</a></p>\n<p>Inference in this kernel relies over only the Users present in Valid Group but what if the user not there how we will predict for that user id</p>",
      "rawMarkdown": "Please pardon me if this is answered some where.\nCan some one help me  in knowing how we can predict for the user ids not in whole train set. \n\nhttps://www.kaggle.com/mpware/sakt-fork?scriptVersionId=48197140\n\nInference in this kernel relies over only the Users present in Valid Group but what if the user not there how we will predict for that user id",
      "votes": null
    },
    {
      "id": "1107363",
      "postDate": "12/09/2020 16:14:06",
      "content": "<p>The test data is loaded in groups. Each group has the information about user answers in the previous group (see data fields \"prior_group_answers_correct\" and \"prior_group_responses\" in the example_test.csv). You can use this information to make predictions for new users.</p>",
      "rawMarkdown": "The test data is loaded in groups. Each group has the information about user answers in the previous group (see data fields \"prior_group_answers_correct\" and \"prior_group_responses\" in the example_test.csv). You can use this information to make predictions for new users.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1107363,
      "author_name": "cleonid",
      "author_url": "",
      "post_date": "12/09/2020 16:14:06",
      "content": "<p>The test data is loaded in groups. Each group has the information about user answers in the previous group (see data fields \"prior_group_answers_correct\" and \"prior_group_responses\" in the example_test.csv). You can use this information to make predictions for new users.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1105771": "Please pardon me if this is answered some where.\nCan some one help me  in knowing how we can predict for the user ids not in whole train set. \n\nhttps://www.kaggle.com/mpware/sakt-fork?scriptVersionId=48197140\n\nInference in this kernel relies over only the Users present in Valid Group but what if the user not there how we will predict for that user id",
    "1107363": "The test data is loaded in groups. Each group has the information about user answers in the previous group (see data fields \"prior_group_answers_correct\" and \"prior_group_responses\" in the example_test.csv). You can use this information to make predictions for new users."
  },
  "source": "meta"
}