{
  "id": 132638,
  "title": "What to do to make this NCAA competition not a gamble with luck?",
  "url": "/competitions/google-cloud-ncaa-march-madness-2020-division-1-womens-tournament/discussion/132638",
  "author_name": "Jerry Pan",
  "post_date": "2020-02-27T02:57:17.444000",
  "votes": 1,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Given the fact that this NCAA competition only provides historical data for validation, it's hard for us to hypertune our models. Since luck often plays a significant role in the sports competition result prediction, could anyone offer some valuable advice on how to hypertune models and perform cross validation?</p>",
  "messages": [
    {
      "id": 757700,
      "postDate": "2020-02-27T02:57:17.443Z",
      "content": "<p>Given the fact that this NCAA competition only provides historical data for validation, it's hard for us to hypertune our models. Since luck often plays a significant role in the sports competition result prediction, could anyone offer some valuable advice on how to hypertune models and perform cross validation?</p>",
      "rawMarkdown": "Given the fact that this NCAA competition only provides historical data for validation, it's hard for us to hypertune our models. Since luck often plays a significant role in the sports competition result prediction, could anyone offer some valuable advice on how to hypertune models and perform cross validation?",
      "votes": 1
    },
    {
      "id": 765633,
      "postDate": "2020-03-06T22:35:44.347Z",
      "rawMarkdown": "",
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 765633,
      "author_name": "",
      "author_url": "",
      "post_date": "2020-03-06T22:35:44.347000",
      "content": "",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "757700": "Given the fact that this NCAA competition only provides historical data for validation, it's hard for us to hypertune our models. Since luck often plays a significant role in the sports competition result prediction, could anyone offer some valuable advice on how to hypertune models and perform cross validation?",
    "765633": ""
  }
}