{
  "id": 348034,
  "title": "What is your strongest feature in this competition?",
  "url": "/competitions/amex-default-prediction/discussion/348034",
  "author_name": "",
  "post_date": "2022-08-26T13:52:54.631186400Z",
  "votes": 2,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Thank you to everyone who participated in the competition and to everyone involved in organizing it.</p>\n<p>I created many features (not in the public code) to improve the accuracy of my single model in this competition.<br>\nHowever, my features did not contribute much to the accuracy.</p>\n<p>What features have you used to improve your scores the most?<br>\nPlease let us know your strongest features.</p>\n<p>◆Our features(exanples)<br>\n・kmeans cluster(n = 4) … Not work<br>\n・state date features … worked a little (CV +0.002pt)<br>\n・PCA … Not work<br>\n・tsfrsh(<a href=\"url\" target=\"_blank\">https://tsfresh.readthedocs.io/en/latest/#</a>)<br>\n　・partial_autocorrelation  …  Not work<br>\n　・autocorrelation …  Not work<br>\n　・c3 …  worked a little (CV +0.002pt)</p>",
  "messages": [
    {
      "id": "1914878",
      "postDate": "08/26/2022 13:52:54",
      "content": "<p>Thank you to everyone who participated in the competition and to everyone involved in organizing it.</p>\n<p>I created many features (not in the public code) to improve the accuracy of my single model in this competition.<br>\nHowever, my features did not contribute much to the accuracy.</p>\n<p>What features have you used to improve your scores the most?<br>\nPlease let us know your strongest features.</p>\n<p>◆Our features(exanples)<br>\n・kmeans cluster(n = 4) … Not work<br>\n・state date features … worked a little (CV +0.002pt)<br>\n・PCA … Not work<br>\n・tsfrsh(<a href=\"url\" target=\"_blank\">https://tsfresh.readthedocs.io/en/latest/#</a>)<br>\n　・partial_autocorrelation  …  Not work<br>\n　・autocorrelation …  Not work<br>\n　・c3 …  worked a little (CV +0.002pt)</p>",
      "rawMarkdown": "Thank you to everyone who participated in the competition and to everyone involved in organizing it.\n\nI created many features (not in the public code) to improve the accuracy of my single model in this competition.\nHowever, my features did not contribute much to the accuracy.\n\nWhat features have you used to improve your scores the most?\nPlease let us know your strongest features.\n\n◆Our features(exanples)\n・kmeans cluster(n = 4) ... Not work\n・state date features ... worked a little (CV +0.002pt)\n・PCA ... Not work\n・tsfrsh([https://tsfresh.readthedocs.io/en/latest/#](url))\n　・partial_autocorrelation  ...  Not work\n　・autocorrelation ...  Not work\n　・c3 ...  worked a little (CV +0.002pt)",
      "votes": null
    },
    {
      "id": "1922115",
      "postDate": "09/01/2022 09:23:37",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/takeshikobayashi\" target=\"_blank\">@takeshikobayashi</a>, May I invite you to participate in this survey regarding your experience on Kaggle (10 min)? This is not a scam. We are a group of researchers at the City University of Hong Kong. The survey link is: <a href=\"https://cityuhk.questionpro.com/survey-of-kaggle-contestants\" target=\"_blank\">https://cityuhk.questionpro.com/survey-of-kaggle-contestants</a></p>",
      "rawMarkdown": "Hi @takeshikobayashi, May I invite you to participate in this survey regarding your experience on Kaggle (10 min)? This is not a scam. We are a group of researchers at the City University of Hong Kong. The survey link is: https://cityuhk.questionpro.com/survey-of-kaggle-contestants",
      "votes": null
    },
    {
      "id": "1924906",
      "postDate": "09/03/2022 14:07:30",
      "content": "<p>Nice Discussion!</p>",
      "rawMarkdown": "Nice Discussion!",
      "votes": null
    },
    {
      "id": "1924907",
      "postDate": "09/03/2022 14:08:40",
      "content": "<p>Thank you!</p>",
      "rawMarkdown": "Thank you!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 1922115,
      "author_name": "lystriving",
      "author_url": "",
      "post_date": "09/01/2022 09:23:37",
      "content": "<p>Hi <a href=\"https://www.kaggle.com/takeshikobayashi\" target=\"_blank\">@takeshikobayashi</a>, May I invite you to participate in this survey regarding your experience on Kaggle (10 min)? This is not a scam. We are a group of researchers at the City University of Hong Kong. The survey link is: <a href=\"https://cityuhk.questionpro.com/survey-of-kaggle-contestants\" target=\"_blank\">https://cityuhk.questionpro.com/survey-of-kaggle-contestants</a></p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 1924906,
      "author_name": "shingot405",
      "author_url": "",
      "post_date": "09/03/2022 14:07:30",
      "content": "<p>Nice Discussion!</p>",
      "votes": null,
      "replies": [
        {
          "id": 1924907,
          "author_name": "takeshikobayashi",
          "author_url": "",
          "post_date": "09/03/2022 14:08:40",
          "content": "<p>Thank you!</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "1914878": "Thank you to everyone who participated in the competition and to everyone involved in organizing it.\n\nI created many features (not in the public code) to improve the accuracy of my single model in this competition.\nHowever, my features did not contribute much to the accuracy.\n\nWhat features have you used to improve your scores the most?\nPlease let us know your strongest features.\n\n◆Our features(exanples)\n・kmeans cluster(n = 4) ... Not work\n・state date features ... worked a little (CV +0.002pt)\n・PCA ... Not work\n・tsfrsh([https://tsfresh.readthedocs.io/en/latest/#](url))\n　・partial_autocorrelation  ...  Not work\n　・autocorrelation ...  Not work\n　・c3 ...  worked a little (CV +0.002pt)",
    "1922115": "Hi @takeshikobayashi, May I invite you to participate in this survey regarding your experience on Kaggle (10 min)? This is not a scam. We are a group of researchers at the City University of Hong Kong. The survey link is: https://cityuhk.questionpro.com/survey-of-kaggle-contestants",
    "1924906": "Nice Discussion!",
    "1924907": "Thank you!"
  },
  "source": "meta"
}