{
  "id": 203059,
  "title": "Is there a timestamp info missing ?",
  "url": "/competitions/riiid-test-answer-prediction/discussion/203059",
  "author_name": "",
  "post_date": "2020-12-13T13:55:52.201734600Z",
  "votes": 7,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi all !</p>\n<p>So, I would like to calculate the reaction_time of a user at the moment he answers a question.</p>\n<p>If I refer to the image below, from SAINT+ paper, both lag_time and reaction_time are important features.<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1161354%2F65d089793560270f518e6b300ec38f74%2FSans%20titre.png?generation=1607867128589858&amp;alt=media\" alt=\"\"></p>\n<p>But as we don't know the lag time between two questions, we cannot infer the reaction_time of the current question, right ?<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1161354%2Fd7a0afbff70f045a578285eebcff8b6c%2FSans%20titre.png?generation=1607867712585536&amp;alt=media\" alt=\"\"></p>\n<p>So the best we can do is approximate lag_time when we have enough data on a user ? Am I right ?</p>",
  "messages": [
    {
      "id": "1111191",
      "postDate": "12/13/2020 13:55:52",
      "content": "<p>Hi all !</p>\n<p>So, I would like to calculate the reaction_time of a user at the moment he answers a question.</p>\n<p>If I refer to the image below, from SAINT+ paper, both lag_time and reaction_time are important features.<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1161354%2F65d089793560270f518e6b300ec38f74%2FSans%20titre.png?generation=1607867128589858&amp;alt=media\" alt=\"\"></p>\n<p>But as we don't know the lag time between two questions, we cannot infer the reaction_time of the current question, right ?<br>\n<img src=\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1161354%2Fd7a0afbff70f045a578285eebcff8b6c%2FSans%20titre.png?generation=1607867712585536&amp;alt=media\" alt=\"\"></p>\n<p>So the best we can do is approximate lag_time when we have enough data on a user ? Am I right ?</p>",
      "rawMarkdown": "Hi all !\n\nSo, I would like to calculate the reaction_time of a user at the moment he answers a question.\n\nIf I refer to the image below, from SAINT+ paper, both lag_time and reaction_time are important features.\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1161354%2F65d089793560270f518e6b300ec38f74%2FSans%20titre.png?generation=1607867128589858&alt=media)\n\nBut as we don't know the lag time between two questions, we cannot infer the reaction_time of the current question, right ?\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1161354%2Fd7a0afbff70f045a578285eebcff8b6c%2FSans%20titre.png?generation=1607867712585536&alt=media)\n\nSo the best we can do is approximate lag_time when we have enough data on a user ? Am I right ?",
      "votes": null
    },
    {
      "id": "1112037",
      "postDate": "12/14/2020 08:21:20",
      "content": "<p>Hi,</p>\n<p>I think this thread can help:</p>\n<p><a href=\"https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/197528\" target=\"_blank\">https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/197528</a></p>\n<p>Basically, notice encoder has eT and decoder has etT-1</p>\n<p>Hope this will clarify.Thanks</p>",
      "rawMarkdown": "Hi,\n\nI think this thread can help:\n\nhttps://www.kaggle.com/c/riiid-test-answer-prediction/discussion/197528\n\nBasically, notice encoder has eT and decoder has etT-1\n\nHope this will clarify.Thanks",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1112037,
      "author_name": "supplejade",
      "author_url": "",
      "post_date": "12/14/2020 08:21:20",
      "content": "<p>Hi,</p>\n<p>I think this thread can help:</p>\n<p><a href=\"https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/197528\" target=\"_blank\">https://www.kaggle.com/c/riiid-test-answer-prediction/discussion/197528</a></p>\n<p>Basically, notice encoder has eT and decoder has etT-1</p>\n<p>Hope this will clarify.Thanks</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1111191": "Hi all !\n\nSo, I would like to calculate the reaction_time of a user at the moment he answers a question.\n\nIf I refer to the image below, from SAINT+ paper, both lag_time and reaction_time are important features.\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1161354%2F65d089793560270f518e6b300ec38f74%2FSans%20titre.png?generation=1607867128589858&alt=media)\n\nBut as we don't know the lag time between two questions, we cannot infer the reaction_time of the current question, right ?\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1161354%2Fd7a0afbff70f045a578285eebcff8b6c%2FSans%20titre.png?generation=1607867712585536&alt=media)\n\nSo the best we can do is approximate lag_time when we have enough data on a user ? Am I right ?",
    "1112037": "Hi,\n\nI think this thread can help:\n\nhttps://www.kaggle.com/c/riiid-test-answer-prediction/discussion/197528\n\nBasically, notice encoder has eT and decoder has etT-1\n\nHope this will clarify.Thanks"
  },
  "source": "meta"
}