{
  "id": 75786,
  "title": "up to 3 months' of historical transactions for each card_id ??",
  "url": "/competitions/elo-merchant-category-recommendation/discussion/75786",
  "author_name": "",
  "post_date": "2018-12-26T15:06:56.868460600Z",
  "votes": 2,
  "comment_count": 2,
  "views": 0,
  "content": "<p>I calculated the observation period of each user with the following code, but there are many users for less than 3 months, for example card_id == \"C_ID_3820ddb105\".. why??\n<code>\ntransactions %&gt;% \n  group_by(card_id) %&gt;% \n  summarise(interval = max(purchase_date) - min(purchase_date))\n</code></p>\n\n<p>Thanks</p>",
  "messages": [
    {
      "id": "445489",
      "postDate": "12/26/2018 15:06:56",
      "content": "<p>I calculated the observation period of each user with the following code, but there are many users for less than 3 months, for example card_id == \"C_ID_3820ddb105\".. why??\n<code>\ntransactions %&gt;% \n  group_by(card_id) %&gt;% \n  summarise(interval = max(purchase_date) - min(purchase_date))\n</code></p>\n\n<p>Thanks</p>",
      "rawMarkdown": "I calculated the observation period of each user with the following code, but there are many users for less than 3 months, for example card_id == \"C_ID_3820ddb105\".. why??\n```\ntransactions %&gt;% \n  group_by(card_id) %&gt;% \n  summarise(interval = max(purchase_date) - min(purchase_date))\n```\n\nThanks",
      "votes": null
    },
    {
      "id": "449974",
      "postDate": "01/04/2019 03:53:53",
      "content": "<p>Cannot understand either. I also have the question about the \"month_lag\" variable. How to understand???</p>",
      "rawMarkdown": "Cannot understand either. I also have the question about the \"month_lag\" variable. How to understand???",
      "votes": null
    },
    {
      "id": "450199",
      "postDate": "01/04/2019 13:38:46",
      "content": "<p>The data explanation says all user have up to 3 month's transaction data. so I think interval time ( max(purchase_date) - min (purchase_data) ) is up to 3 month's, but it's not.</p>\n\n<p>I think that \"month_lag\" is a lag based on the reference date for each user. so reference date is different from user to user.</p>",
      "rawMarkdown": "The data explanation says all user have up to 3 month's transaction data. so I think interval time ( max(purchase_date) - min (purchase_data) ) is up to 3 month's, but it's not.\n\nI think that \"month_lag\" is a lag based on the reference date for each user. so reference date is different from user to user.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 449974,
      "author_name": "amudanninhong",
      "author_url": "",
      "post_date": "01/04/2019 03:53:53",
      "content": "<p>Cannot understand either. I also have the question about the \"month_lag\" variable. How to understand???</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 450199,
      "author_name": "taku0831",
      "author_url": "",
      "post_date": "01/04/2019 13:38:46",
      "content": "<p>The data explanation says all user have up to 3 month's transaction data. so I think interval time ( max(purchase_date) - min (purchase_data) ) is up to 3 month's, but it's not.</p>\n\n<p>I think that \"month_lag\" is a lag based on the reference date for each user. so reference date is different from user to user.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "445489": "I calculated the observation period of each user with the following code, but there are many users for less than 3 months, for example card_id == \"C_ID_3820ddb105\".. why??\n```\ntransactions %&gt;% \n  group_by(card_id) %&gt;% \n  summarise(interval = max(purchase_date) - min(purchase_date))\n```\n\nThanks",
    "449974": "Cannot understand either. I also have the question about the \"month_lag\" variable. How to understand???",
    "450199": "The data explanation says all user have up to 3 month's transaction data. so I think interval time ( max(purchase_date) - min (purchase_data) ) is up to 3 month's, but it's not.\n\nI think that \"month_lag\" is a lag based on the reference date for each user. so reference date is different from user to user."
  },
  "source": "meta"
}