{
  "id": 85147,
  "title": "My stable solution to get a bronze medal",
  "url": "/competitions/vsb-power-line-fault-detection/discussion/85147",
  "author_name": "Daisuke Shibato",
  "post_date": "2019-03-22T01:00:54.738000",
  "votes": 2,
  "comment_count": 0,
  "views": 0,
  "content": "<p>After reviewing my submissions, I found that\n- Solutions with a single LSTM model tend to have a huge shakedown\n- Solutions with a single LightGBM model tend to have a huge <strong>shakeup</strong> (such as public 0.521 and private 0.698).\n- Ensembling/Stacking of LSTM and LightGBM models were stable and had just ± 0.02.</p>",
  "messages": [
    {
      "id": 496199,
      "postDate": "2019-03-22T01:00:54.740Z",
      "content": "<p>After reviewing my submissions, I found that\n- Solutions with a single LSTM model tend to have a huge shakedown\n- Solutions with a single LightGBM model tend to have a huge <strong>shakeup</strong> (such as public 0.521 and private 0.698).\n- Ensembling/Stacking of LSTM and LightGBM models were stable and had just ± 0.02.</p>",
      "rawMarkdown": "After reviewing my submissions, I found that\n- Solutions with a single LSTM model tend to have a huge shakedown\n- Solutions with a single LightGBM model tend to have a huge **shakeup** (such as public 0.521 and private 0.698).\n- Ensembling/Stacking of LSTM and LightGBM models were stable and had just ± 0.02.",
      "votes": 2
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "496199": "After reviewing my submissions, I found that\n- Solutions with a single LSTM model tend to have a huge shakedown\n- Solutions with a single LightGBM model tend to have a huge **shakeup** (such as public 0.521 and private 0.698).\n- Ensembling/Stacking of LSTM and LightGBM models were stable and had just ± 0.02."
  }
}