{
  "id": 68675,
  "title": "Are features normalized by the transaction revenue useful?",
  "url": "/competitions/ga-customer-revenue-prediction/discussion/68675",
  "author_name": "akKaggle",
  "post_date": "2018-10-16T03:12:13.501000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi,</p>\n\n<p>I am trying to normalize some features in the train set by the sum of all the transactionRevenue values.</p>\n\n<p>The problem is that in the test set transactionRevenue is not available, so are these normalized features still useful and what are some ways to get around this problem?</p>\n\n<p>akKaggle</p>",
  "messages": [
    {
      "id": 404587,
      "postDate": "2018-10-16T03:12:13.500Z",
      "content": "<p>Hi,</p>\n\n<p>I am trying to normalize some features in the train set by the sum of all the transactionRevenue values.</p>\n\n<p>The problem is that in the test set transactionRevenue is not available, so are these normalized features still useful and what are some ways to get around this problem?</p>\n\n<p>akKaggle</p>",
      "rawMarkdown": "Hi,\n\nI am trying to normalize some features in the train set by the sum of all the transactionRevenue values.\n\nThe problem is that in the test set transactionRevenue is not available, so are these normalized features still useful and what are some ways to get around this problem?\n\nakKaggle"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "404587": "Hi,\n\nI am trying to normalize some features in the train set by the sum of all the transactionRevenue values.\n\nThe problem is that in the test set transactionRevenue is not available, so are these normalized features still useful and what are some ways to get around this problem?\n\nakKaggle"
  }
}