{
  "id": 310363,
  "title": "Evaluation Criteria",
  "url": "/competitions/h-and-m-personalized-fashion-recommendations/discussion/310363",
  "author_name": "",
  "post_date": "2022-03-01T01:27:30.426380100Z",
  "votes": 2,
  "comment_count": 3,
  "views": 0,
  "content": "<p>The Evaluation page say</p>\n<p>\"Customer that did not make any purchase during test period are excluded from the scoring.\"</p>\n<p>I am sure how to interpret it. Please advise.</p>",
  "messages": [
    {
      "id": "1707972",
      "postDate": "03/01/2022 01:27:30",
      "content": "<p>The Evaluation page say</p>\n<p>\"Customer that did not make any purchase during test period are excluded from the scoring.\"</p>\n<p>I am sure how to interpret it. Please advise.</p>",
      "rawMarkdown": "The Evaluation page say\n\n\"Customer that did not make any purchase during test period are excluded from the scoring.\"\n\nI am sure how to interpret it. Please advise.",
      "votes": null
    },
    {
      "id": "1708648",
      "postDate": "03/01/2022 15:40:18",
      "content": "<p>During scoring, for each customer we compute <code>mAP@12</code>. Then our LB score is the average of all these customer <code>mAP@12</code>. What they are saying is that when computing the average of all customers, we exclude all customers who didn't buy anything during the test dataset evaluation time period (because their <code>mAP@12</code> will be meaningless).</p>",
      "rawMarkdown": "During scoring, for each customer we compute `mAP@12`. Then our LB score is the average of all these customer `mAP@12`. What they are saying is that when computing the average of all customers, we exclude all customers who didn't buy anything during the test dataset evaluation time period (because their `mAP@12` will be meaningless).",
      "votes": null
    },
    {
      "id": "1709015",
      "postDate": "03/01/2022 22:10:19",
      "content": "<p><a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> </p>\n<p><a href=\"https://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152\" target=\"_blank\">https://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152</a></p>\n<p>The other discussion elaborates my point.. </p>",
      "rawMarkdown": "cdeotte \n\nhttps://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152\n\nThe other discussion elaborates my point..",
      "votes": null
    },
    {
      "id": "1722808",
      "postDate": "03/14/2022 21:58:24",
      "content": "<p>The Evaluation Metric has been updated.</p>\n<p><a href=\"https://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152#1722777\" target=\"_blank\">https://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152#1722777</a></p>",
      "rawMarkdown": "The Evaluation Metric has been updated.\n\nhttps://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152#1722777",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1708648,
      "author_name": "cdeotte",
      "author_url": "",
      "post_date": "03/01/2022 15:40:18",
      "content": "<p>During scoring, for each customer we compute <code>mAP@12</code>. Then our LB score is the average of all these customer <code>mAP@12</code>. What they are saying is that when computing the average of all customers, we exclude all customers who didn't buy anything during the test dataset evaluation time period (because their <code>mAP@12</code> will be meaningless).</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1709015,
      "author_name": "atulverma",
      "author_url": "",
      "post_date": "03/01/2022 22:10:19",
      "content": "<p><a href=\"https://www.kaggle.com/cdeotte\" target=\"_blank\">@cdeotte</a> </p>\n<p><a href=\"https://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152\" target=\"_blank\">https://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152</a></p>\n<p>The other discussion elaborates my point.. </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1722808,
      "author_name": "atulverma",
      "author_url": "",
      "post_date": "03/14/2022 21:58:24",
      "content": "<p>The Evaluation Metric has been updated.</p>\n<p><a href=\"https://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152#1722777\" target=\"_blank\">https://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152#1722777</a></p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "1707972": "The Evaluation page say\n\n\"Customer that did not make any purchase during test period are excluded from the scoring.\"\n\nI am sure how to interpret it. Please advise.",
    "1708648": "During scoring, for each customer we compute `mAP@12`. Then our LB score is the average of all these customer `mAP@12`. What they are saying is that when computing the average of all customers, we exclude all customers who didn't buy anything during the test dataset evaluation time period (because their `mAP@12` will be meaningless).",
    "1709015": "cdeotte \n\nhttps://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152\n\nThe other discussion elaborates my point..",
    "1722808": "The Evaluation Metric has been updated.\n\nhttps://www.kaggle.com/c/h-and-m-personalized-fashion-recommendations/discussion/309152#1722777"
  },
  "source": "meta"
}