{
  "id": 2079,
  "title": "Multiple Accounts",
  "url": "/competitions/FacebookRecruiting/discussion/2079",
  "author_name": "",
  "post_date": "2012-06-25T16:32:25.143Z",
  "votes": 3,
  "comment_count": 3,
  "views": 3240,
  "content": "<p>A brief reminder, when you registered for the competition, you accepted Kaggle's terms and conditions, including:</p>\r\n<p><strong>you cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts;</strong></p>\r\n<p>Using multiple accounts in grounds for removal from the competition.</p>",
  "messages": [
    {
      "id": "11873",
      "postDate": "06/25/2012 16:32:25",
      "content": "<p>A brief reminder, when you registered for the competition, you accepted Kaggle's terms and conditions, including:</p>\r\n<p><strong>you cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts;</strong></p>\r\n<p>Using multiple accounts in grounds for removal from the competition.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "11878",
      "postDate": "06/25/2012 18:32:30",
      "content": "<p>Kaggle doesn't need to treat people like that. There are always different ways to use different accounts to login. Yes, indeed, they can track down somehow but still there are ways to hide. In addition, enthusiastic people may work hard and would like to\r\n test their ideas as soon as they get something running, why not let them evaluate freely? Of course, if they are abusing the system, they shall be banned nevertheless.</p>\r\n<p>Still, I don't understand the exact purpose of this rule. </p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "11879",
      "postDate": "06/25/2012 18:46:14",
      "content": "<p>Yes, it does.<br>\r\nWhat do you think is the difference between &quot;enthusiastic people&quot; and &quot;abusing the system&quot;?<br>\r\n(some crazy people are actually using CV to test ideas :) )</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "11898",
      "postDate": "06/26/2012 15:57:31",
      "content": "<p>I agree that 2 submissions is a low number, maybe 3-5 would be better. <br>\r\nBut yes, we can use cross-validation set to, at least, know that our scores are incresing/descreasing. We could select some random nodes from training that do not overlap with testing and predicting for them. Measure Map@10 or AUC.\r\n<br>\r\nOf course the score wouldn't directly relate to the leaderboard ones, but generally an improvement over this measurement would reflect an improvement in the leaderboard (unless overfitting, it is).\r\n</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 11878,
      "author_name": "begentle",
      "author_url": "",
      "post_date": "06/25/2012 18:32:30",
      "content": "<p>Kaggle doesn't need to treat people like that. There are always different ways to use different accounts to login. Yes, indeed, they can track down somehow but still there are ways to hide. In addition, enthusiastic people may work hard and would like to\r\n test their ideas as soon as they get something running, why not let them evaluate freely? Of course, if they are abusing the system, they shall be banned nevertheless.</p>\r\n<p>Still, I don't understand the exact purpose of this rule. </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 11879,
      "author_name": "ccccat",
      "author_url": "",
      "post_date": "06/25/2012 18:46:14",
      "content": "<p>Yes, it does.<br>\r\nWhat do you think is the difference between &quot;enthusiastic people&quot; and &quot;abusing the system&quot;?<br>\r\n(some crazy people are actually using CV to test ideas :) )</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 11898,
      "author_name": "leustagos",
      "author_url": "",
      "post_date": "06/26/2012 15:57:31",
      "content": "<p>I agree that 2 submissions is a low number, maybe 3-5 would be better. <br>\r\nBut yes, we can use cross-validation set to, at least, know that our scores are incresing/descreasing. We could select some random nodes from training that do not overlap with testing and predicting for them. Measure Map@10 or AUC.\r\n<br>\r\nOf course the score wouldn't directly relate to the leaderboard ones, but generally an improvement over this measurement would reflect an improvement in the leaderboard (unless overfitting, it is).\r\n</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "11873": "",
    "11878": "",
    "11879": "",
    "11898": ""
  },
  "source": "meta"
}