{
  "id": 73516,
  "title": "Loyalty score",
  "url": "/competitions/elo-merchant-category-recommendation/discussion/73516",
  "author_name": "corner200",
  "post_date": "2018-12-03T18:20:29.636000",
  "votes": 7,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hello,\nin Data Dictionary.xlsx its written, that\n\"Loyalty numerical score calculated 2 months after historical and evaluation period\"</p>\n\n<p>what is the historical period?\nwhat is the evaluation period?</p>\n\n<p>historical_transactions goes from 2017-01-01 00:00:08 to 2018-02-28 23:59:51\nnew_merchant_transactions goes from 2017-03-01 03:24:51 to 2018-04-30 23:59:59</p>\n\n<p>is historical period from 2017-01-01 00:00:08 to 2018-02-28 23:59:51? Thats 14 months\nand evaluation period from 2017-03-01 03:24:51 to 2018-04-30 23:59:59? Thats also 14 months</p>\n\n<p>I don't really get the difference between historical_transactions and new_merchant_transactions.</p>\n\n<p>\"historical_transactions.csv contains up to 3 months' worth of transactions for every card at any of the provided merchant_ids.\nnew_merchant_transactions.csv contains the transactions at new merchants (merchant_ids that this particular card_id has not yet visited) over a period of two months.\"</p>\n\n<p>Does \"up to\" mean \"less then\"?\nBut historical_transactions is 14 months not 3 months.\nAnd C_ID_00007093c1 visited M_ID_57df19bf28 on 10 different months not 3 months.</p>\n\n<p>In <a href=\"https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/72993#430638\">https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/72993#430638</a> Addison Howard writes \"That is correct \" to the question \"can you please clarify the target? are we supposed to predict the loyalty score for the dates 1/5/2018 to 30/6/2018? \"\nSo the target in train.csv is calculated for 1/5/2018 to 30/6/2018?\nAnd we have to predict the target for the test.csv for 1/5/2018 to 30/6/2018. Is that correct?</p>\n\n<p>Thank you very much</p>",
  "messages": [
    {
      "id": 432330,
      "postDate": "2018-12-03T18:20:29.637Z",
      "content": "<p>Hello,\nin Data Dictionary.xlsx its written, that\n\"Loyalty numerical score calculated 2 months after historical and evaluation period\"</p>\n\n<p>what is the historical period?\nwhat is the evaluation period?</p>\n\n<p>historical_transactions goes from 2017-01-01 00:00:08 to 2018-02-28 23:59:51\nnew_merchant_transactions goes from 2017-03-01 03:24:51 to 2018-04-30 23:59:59</p>\n\n<p>is historical period from 2017-01-01 00:00:08 to 2018-02-28 23:59:51? Thats 14 months\nand evaluation period from 2017-03-01 03:24:51 to 2018-04-30 23:59:59? Thats also 14 months</p>\n\n<p>I don't really get the difference between historical_transactions and new_merchant_transactions.</p>\n\n<p>\"historical_transactions.csv contains up to 3 months' worth of transactions for every card at any of the provided merchant_ids.\nnew_merchant_transactions.csv contains the transactions at new merchants (merchant_ids that this particular card_id has not yet visited) over a period of two months.\"</p>\n\n<p>Does \"up to\" mean \"less then\"?\nBut historical_transactions is 14 months not 3 months.\nAnd C_ID_00007093c1 visited M_ID_57df19bf28 on 10 different months not 3 months.</p>\n\n<p>In <a href=\"https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/72993#430638\">https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/72993#430638</a> Addison Howard writes \"That is correct \" to the question \"can you please clarify the target? are we supposed to predict the loyalty score for the dates 1/5/2018 to 30/6/2018? \"\nSo the target in train.csv is calculated for 1/5/2018 to 30/6/2018?\nAnd we have to predict the target for the test.csv for 1/5/2018 to 30/6/2018. Is that correct?</p>\n\n<p>Thank you very much</p>",
      "rawMarkdown": "Hello,\nin Data Dictionary.xlsx its written, that\n\"Loyalty numerical score calculated 2 months after historical and evaluation period\"\n\nwhat is the historical period?\nwhat is the evaluation period?\n\nhistorical_transactions goes from 2017-01-01 00:00:08 to 2018-02-28 23:59:51\nnew_merchant_transactions goes from 2017-03-01 03:24:51 to 2018-04-30 23:59:59\n\nis historical period from 2017-01-01 00:00:08 to 2018-02-28 23:59:51? Thats 14 months\nand evaluation period from 2017-03-01 03:24:51 to 2018-04-30 23:59:59? Thats also 14 months\n\nI don't really get the difference between historical_transactions and new_merchant_transactions.\n\n\"historical_transactions.csv contains up to 3 months' worth of transactions for every card at any of the provided merchant_ids.\nnew_merchant_transactions.csv contains the transactions at new merchants (merchant_ids that this particular card_id has not yet visited) over a period of two months.\"\n\nDoes \"up to\" mean \"less then\"?\nBut historical_transactions is 14 months not 3 months.\nAnd C_ID_00007093c1 visited M_ID_57df19bf28 on 10 different months not 3 months.\n\nIn https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/72993#430638 Addison Howard writes \"That is correct \" to the question \"can you please clarify the target? are we supposed to predict the loyalty score for the dates 1/5/2018 to 30/6/2018? \"\nSo the target in train.csv is calculated for 1/5/2018 to 30/6/2018?\nAnd we have to predict the target for the test.csv for 1/5/2018 to 30/6/2018. Is that correct?\n\nThank you very much",
      "votes": 7
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "432330": "Hello,\nin Data Dictionary.xlsx its written, that\n\"Loyalty numerical score calculated 2 months after historical and evaluation period\"\n\nwhat is the historical period?\nwhat is the evaluation period?\n\nhistorical_transactions goes from 2017-01-01 00:00:08 to 2018-02-28 23:59:51\nnew_merchant_transactions goes from 2017-03-01 03:24:51 to 2018-04-30 23:59:59\n\nis historical period from 2017-01-01 00:00:08 to 2018-02-28 23:59:51? Thats 14 months\nand evaluation period from 2017-03-01 03:24:51 to 2018-04-30 23:59:59? Thats also 14 months\n\nI don't really get the difference between historical_transactions and new_merchant_transactions.\n\n\"historical_transactions.csv contains up to 3 months' worth of transactions for every card at any of the provided merchant_ids.\nnew_merchant_transactions.csv contains the transactions at new merchants (merchant_ids that this particular card_id has not yet visited) over a period of two months.\"\n\nDoes \"up to\" mean \"less then\"?\nBut historical_transactions is 14 months not 3 months.\nAnd C_ID_00007093c1 visited M_ID_57df19bf28 on 10 different months not 3 months.\n\nIn https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/72993#430638 Addison Howard writes \"That is correct \" to the question \"can you please clarify the target? are we supposed to predict the loyalty score for the dates 1/5/2018 to 30/6/2018? \"\nSo the target in train.csv is calculated for 1/5/2018 to 30/6/2018?\nAnd we have to predict the target for the test.csv for 1/5/2018 to 30/6/2018. Is that correct?\n\nThank you very much"
  }
}