{
  "id": 79468,
  "title": "Timeline ",
  "url": "/competitions/elo-merchant-category-recommendation/discussion/79468",
  "author_name": "",
  "post_date": "2019-02-04T13:04:31.507588Z",
  "votes": null,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hello everyone,\nI have seen some discussions regarding this matter and still I am not able to realize WHEN the score is calculated.</p>\n\n<p>The way I see it until some period X all customers had some transactions made (that may or may not be presented in the data) . Afterwards, ELO has used some ML model to advertise to customers ,then new transactions occurred (which definitely should be in the data) for some period Y . \nat the end of periods X+Y ELO has presented a \"loyalty score \"\nCould someone please explain to me how to obtain X +Y, X,Y from the data or at least contribute with some relevant idea.\nOtherwise, I don't understand how are we suppose to obtain any insights from the transaction data.</p>\n\n<p>Thank you</p>",
  "messages": [
    {
      "id": "465976",
      "postDate": "02/04/2019 13:04:31",
      "content": "<p>Hello everyone,\nI have seen some discussions regarding this matter and still I am not able to realize WHEN the score is calculated.</p>\n\n<p>The way I see it until some period X all customers had some transactions made (that may or may not be presented in the data) . Afterwards, ELO has used some ML model to advertise to customers ,then new transactions occurred (which definitely should be in the data) for some period Y . \nat the end of periods X+Y ELO has presented a \"loyalty score \"\nCould someone please explain to me how to obtain X +Y, X,Y from the data or at least contribute with some relevant idea.\nOtherwise, I don't understand how are we suppose to obtain any insights from the transaction data.</p>\n\n<p>Thank you</p>",
      "rawMarkdown": "Hello everyone,\nI have seen some discussions regarding this matter and still I am not able to realize WHEN the score is calculated.\n\nThe way I see it until some period X all customers had some transactions made (that may or may not be presented in the data) . Afterwards, ELO has used some ML model to advertise to customers ,then new transactions occurred (which definitely should be in the data) for some period Y . \nat the end of periods X+Y ELO has presented a \"loyalty score \"\nCould someone please explain to me how to obtain X +Y, X,Y from the data or at least contribute with some relevant idea.\nOtherwise, I don't understand how are we suppose to obtain any insights from the transaction data.\n\nThank you",
      "votes": null
    },
    {
      "id": "466778",
      "postDate": "02/05/2019 23:02:35",
      "content": "<p>I think that the loyalty score is calculated from a formula with every variable being in the data that they gave us: there is no period Y.  The reason I think this is because the data is artificially created (it says so on the Data tab), so Elo would have had to make up the transactions in period y through predicting them, which I find hard to believe.  I talk about it in my discussion:\n<a href=\"https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/79440\">https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/79440</a></p>",
      "rawMarkdown": "I think that the loyalty score is calculated from a formula with every variable being in the data that they gave us: there is no period Y.  The reason I think this is because the data is artificially created (it says so on the Data tab), so Elo would have had to make up the transactions in period y through predicting them, which I find hard to believe.  I talk about it in my discussion:\nhttps://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/79440",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 466778,
      "author_name": "petersk20",
      "author_url": "",
      "post_date": "02/05/2019 23:02:35",
      "content": "<p>I think that the loyalty score is calculated from a formula with every variable being in the data that they gave us: there is no period Y.  The reason I think this is because the data is artificially created (it says so on the Data tab), so Elo would have had to make up the transactions in period y through predicting them, which I find hard to believe.  I talk about it in my discussion:\n<a href=\"https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/79440\">https://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/79440</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "465976": "Hello everyone,\nI have seen some discussions regarding this matter and still I am not able to realize WHEN the score is calculated.\n\nThe way I see it until some period X all customers had some transactions made (that may or may not be presented in the data) . Afterwards, ELO has used some ML model to advertise to customers ,then new transactions occurred (which definitely should be in the data) for some period Y . \nat the end of periods X+Y ELO has presented a \"loyalty score \"\nCould someone please explain to me how to obtain X +Y, X,Y from the data or at least contribute with some relevant idea.\nOtherwise, I don't understand how are we suppose to obtain any insights from the transaction data.\n\nThank you",
    "466778": "I think that the loyalty score is calculated from a formula with every variable being in the data that they gave us: there is no period Y.  The reason I think this is because the data is artificially created (it says so on the Data tab), so Elo would have had to make up the transactions in period y through predicting them, which I find hard to believe.  I talk about it in my discussion:\nhttps://www.kaggle.com/c/elo-merchant-category-recommendation/discussion/79440"
  },
  "source": "meta"
}