{
  "id": 121129,
  "title": "similar competition recommendation ",
  "url": "/competitions/ashrae-energy-prediction/discussion/121129",
  "author_name": "",
  "post_date": "2019-12-11T10:16:00.007020600Z",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Hey, can you guys please recommend me some/a similar competition/s, so I can learn how to better feature engineering, selection or model building. Since most possibly I can find some open source solutions.  Many thanks! </p>",
  "messages": [
    {
      "id": "692482",
      "postDate": "12/11/2019 10:16:00",
      "content": "<p>Hey, can you guys please recommend me some/a similar competition/s, so I can learn how to better feature engineering, selection or model building. Since most possibly I can find some open source solutions.  Many thanks! </p>",
      "rawMarkdown": "Hey, can you guys please recommend me some/a similar competition/s, so I can learn how to better feature engineering, selection or model building. Since most possibly I can find some open source solutions.  Many thanks!",
      "votes": null
    },
    {
      "id": "693867",
      "postDate": "12/12/2019 21:45:26",
      "content": "<p>Maybe you can use some ideas from <a href=\"https://www.kaggle.com/novinsh/surprise-me-2-with-lstm\">this competition</a> for feature engineering, although the competition context is a bit different, the features (those that explain some statistics such as min, max, median, difference, etc.) could be useful!</p>",
      "rawMarkdown": "Maybe you can use some ideas from [this competition](https://www.kaggle.com/novinsh/surprise-me-2-with-lstm) for feature engineering, although the competition context is a bit different, the features (those that explain some statistics such as min, max, median, difference, etc.) could be useful!",
      "votes": null
    },
    {
      "id": "696182",
      "postDate": "12/16/2019 08:23:49",
      "content": "<p>Thank you so much! </p>",
      "rawMarkdown": "Thank you so much!",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 693867,
      "author_name": "novinsh",
      "author_url": "",
      "post_date": "12/12/2019 21:45:26",
      "content": "<p>Maybe you can use some ideas from <a href=\"https://www.kaggle.com/novinsh/surprise-me-2-with-lstm\">this competition</a> for feature engineering, although the competition context is a bit different, the features (those that explain some statistics such as min, max, median, difference, etc.) could be useful!</p>",
      "votes": null,
      "replies": [
        {
          "id": 696182,
          "author_name": "wangshuailong",
          "author_url": "",
          "post_date": "12/16/2019 08:23:49",
          "content": "<p>Thank you so much! </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "692482": "Hey, can you guys please recommend me some/a similar competition/s, so I can learn how to better feature engineering, selection or model building. Since most possibly I can find some open source solutions.  Many thanks!",
    "693867": "Maybe you can use some ideas from [this competition](https://www.kaggle.com/novinsh/surprise-me-2-with-lstm) for feature engineering, although the competition context is a bit different, the features (those that explain some statistics such as min, max, median, difference, etc.) could be useful!",
    "696182": "Thank you so much!"
  },
  "source": "meta"
}