{
  "id": 94845,
  "title": "One Feature, No ML, Gold Medal Range",
  "url": "/competitions/LANL-Earthquake-Prediction/writeups/trent-one-feature-no-ml-gold-medal-range",
  "author_name": "",
  "post_date": "2019-06-07T11:01:12.407080500Z",
  "votes": 2,
  "comment_count": 3,
  "views": 0,
  "content": "<p>I have created a <a href=\"https://www.kaggle.com/trentb/one-feature-no-ml-gold-medal-range\">kernel</a> that demonstrates the ability to achieve a high score (private leaderboard: 2.33037; 9th place) in the LANL Earthquake Prediction competition with only <strong>one</strong> well-crafted feature, no machine learning, and peak TTF information from the test set data leak.</p>",
  "messages": [
    {
      "id": "547167",
      "postDate": "06/07/2019 11:01:12",
      "content": "<p>I have created a <a href=\"https://www.kaggle.com/trentb/one-feature-no-ml-gold-medal-range\">kernel</a> that demonstrates the ability to achieve a high score (private leaderboard: 2.33037; 9th place) in the LANL Earthquake Prediction competition with only <strong>one</strong> well-crafted feature, no machine learning, and peak TTF information from the test set data leak.</p>",
      "rawMarkdown": "I have created a [kernel](https://www.kaggle.com/trentb/one-feature-no-ml-gold-medal-range) that demonstrates the ability to achieve a high score (private leaderboard: 2.33037; 9th place) in the LANL Earthquake Prediction competition with only **one** well-crafted feature, no machine learning, and peak TTF information from the test set data leak.",
      "votes": null
    },
    {
      "id": "547179",
      "postDate": "06/07/2019 11:20:23",
      "content": "<p>That's very nice :)\nThe data leak really added a lot of information.</p>",
      "rawMarkdown": "That's very nice :)\nThe data leak really added a lot of information.",
      "votes": null
    },
    {
      "id": "547186",
      "postDate": "06/07/2019 11:30:22",
      "content": "<p>With rescaling to test mean so many people would get to gold range that it is no longer a gold range ;)</p>\n\n<p>What would have been interested is to see this submitted before competition end, not after.  Did you think of it only after competition end?</p>",
      "rawMarkdown": "With rescaling to test mean so many people would get to gold range that it is no longer a gold range ;)\n\nWhat would have been interested is to see this submitted before competition end, not after.  Did you think of it only after competition end?",
      "votes": null
    },
    {
      "id": "547215",
      "postDate": "06/07/2019 12:17:53",
      "content": "<p>Yes, this was submitted out of curiosity after the competition when I fully realized how important scaling to the test mean was.</p>\n\n<p>During the competition I submitted an unscaled-to-test-mean submission of the one feature, but I then abandoned the idea.</p>",
      "rawMarkdown": "Yes, this was submitted out of curiosity after the competition when I fully realized how important scaling to the test mean was.\n\nDuring the competition I submitted an unscaled-to-test-mean submission of the one feature, but I then abandoned the idea.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 547179,
      "author_name": "ricarddelgado",
      "author_url": "",
      "post_date": "06/07/2019 11:20:23",
      "content": "<p>That's very nice :)\nThe data leak really added a lot of information.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 547186,
      "author_name": "cpmpml",
      "author_url": "",
      "post_date": "06/07/2019 11:30:22",
      "content": "<p>With rescaling to test mean so many people would get to gold range that it is no longer a gold range ;)</p>\n\n<p>What would have been interested is to see this submitted before competition end, not after.  Did you think of it only after competition end?</p>",
      "votes": null,
      "replies": [
        {
          "id": 547215,
          "author_name": "trentb",
          "author_url": "",
          "post_date": "06/07/2019 12:17:53",
          "content": "<p>Yes, this was submitted out of curiosity after the competition when I fully realized how important scaling to the test mean was.</p>\n\n<p>During the competition I submitted an unscaled-to-test-mean submission of the one feature, but I then abandoned the idea.</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "547167": "I have created a [kernel](https://www.kaggle.com/trentb/one-feature-no-ml-gold-medal-range) that demonstrates the ability to achieve a high score (private leaderboard: 2.33037; 9th place) in the LANL Earthquake Prediction competition with only **one** well-crafted feature, no machine learning, and peak TTF information from the test set data leak.",
    "547179": "That's very nice :)\nThe data leak really added a lot of information.",
    "547186": "With rescaling to test mean so many people would get to gold range that it is no longer a gold range ;)\n\nWhat would have been interested is to see this submitted before competition end, not after.  Did you think of it only after competition end?",
    "547215": "Yes, this was submitted out of curiosity after the competition when I fully realized how important scaling to the test mean was.\n\nDuring the competition I submitted an unscaled-to-test-mean submission of the one feature, but I then abandoned the idea."
  },
  "source": "meta"
}