{
  "id": 64600,
  "title": "Simple feature that made public kernels top 50 (and thanks!)",
  "url": "/competitions/home-credit-default-risk/discussion/64600",
  "author_name": "James Davis",
  "post_date": "2018-08-30T16:07:35.932000",
  "votes": 14,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Thanks so much to Oliver, Will Koehrsen, Scripus, Aguiar,  Ann Antonova, Andy Harless and every one of the teachers and contributors on Kaggle.  It's been an informative, challenging, and rewarding experience, and your contributions really make a difference in people's lives.  I didn't know what cross validation meant 2 months ago- Learn by doing!</p>\n\n<p>This small kernel predicts the loan term length (easy, since loan terms are binned) and computes real interest rates on the loans.  Obviously, that's a good indicator of risk. \n I stacked once with this and a couple derivative features, and rank averaged.  </p>\n\n<p>I'm not sure (but very curious) if other solutions used this idea - Home Credit clearly intended for people <em>not</em> to, since they removed loan term lengths from their application data. <br>\n<a href=\"https://www.kaggle.com/lorentztrans/final-cnt-generator/\">https://www.kaggle.com/lorentztrans/final-cnt-generator/</a></p>",
  "messages": [
    {
      "id": 378873,
      "postDate": "2018-08-30T16:07:35.933Z",
      "content": "<p>Thanks so much to Oliver, Will Koehrsen, Scripus, Aguiar,  Ann Antonova, Andy Harless and every one of the teachers and contributors on Kaggle.  It's been an informative, challenging, and rewarding experience, and your contributions really make a difference in people's lives.  I didn't know what cross validation meant 2 months ago- Learn by doing!</p>\n\n<p>This small kernel predicts the loan term length (easy, since loan terms are binned) and computes real interest rates on the loans.  Obviously, that's a good indicator of risk. \n I stacked once with this and a couple derivative features, and rank averaged.  </p>\n\n<p>I'm not sure (but very curious) if other solutions used this idea - Home Credit clearly intended for people <em>not</em> to, since they removed loan term lengths from their application data. <br>\n<a href=\"https://www.kaggle.com/lorentztrans/final-cnt-generator/\">https://www.kaggle.com/lorentztrans/final-cnt-generator/</a></p>",
      "rawMarkdown": "Thanks so much to Oliver, Will Koehrsen, Scripus, Aguiar,  Ann Antonova, Andy Harless and every one of the teachers and contributors on Kaggle.  It's been an informative, challenging, and rewarding experience, and your contributions really make a difference in people's lives.  I didn't know what cross validation meant 2 months ago- Learn by doing!\n\nThis small kernel predicts the loan term length (easy, since loan terms are binned) and computes real interest rates on the loans.  Obviously, that's a good indicator of risk. \n I stacked once with this and a couple derivative features, and rank averaged.  \n\nI'm not sure (but very curious) if other solutions used this idea - Home Credit clearly intended for people *not* to, since they removed loan term lengths from their application data.  \nhttps://www.kaggle.com/lorentztrans/final-cnt-generator/",
      "votes": 14
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "378873": "Thanks so much to Oliver, Will Koehrsen, Scripus, Aguiar,  Ann Antonova, Andy Harless and every one of the teachers and contributors on Kaggle.  It's been an informative, challenging, and rewarding experience, and your contributions really make a difference in people's lives.  I didn't know what cross validation meant 2 months ago- Learn by doing!\n\nThis small kernel predicts the loan term length (easy, since loan terms are binned) and computes real interest rates on the loans.  Obviously, that's a good indicator of risk. \n I stacked once with this and a couple derivative features, and rank averaged.  \n\nI'm not sure (but very curious) if other solutions used this idea - Home Credit clearly intended for people *not* to, since they removed loan term lengths from their application data.  \nhttps://www.kaggle.com/lorentztrans/final-cnt-generator/"
  }
}