{
  "id": 59236,
  "title": "Idea of using user_id columns",
  "url": "/competitions/avito-demand-prediction/discussion/59236",
  "author_name": "hapsei",
  "post_date": "2018-06-20T02:08:11.295000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p><a href=\"https://www.kaggle.com/bminixhofer/aggregated-features-lightgbm\">https://www.kaggle.com/bminixhofer/aggregated-features-lightgbm</a></p>\n\n<p>According to this notebook, there is a common user in train and test.\nPast user's deal_probability is to predict deal_probability of future user\nIt will be a very useful feature quantity.</p>\n\n<p>Divide test with common users and users not common,\nand trying target_encode!</p>\n\n<p>Although it did not work very well in my implementation\nPlease use this idea successfully</p>",
  "messages": [
    {
      "id": 345524,
      "postDate": "2018-06-20T02:08:11.297Z",
      "content": "<p><a href=\"https://www.kaggle.com/bminixhofer/aggregated-features-lightgbm\">https://www.kaggle.com/bminixhofer/aggregated-features-lightgbm</a></p>\n\n<p>According to this notebook, there is a common user in train and test.\nPast user's deal_probability is to predict deal_probability of future user\nIt will be a very useful feature quantity.</p>\n\n<p>Divide test with common users and users not common,\nand trying target_encode!</p>\n\n<p>Although it did not work very well in my implementation\nPlease use this idea successfully</p>",
      "rawMarkdown": "https://www.kaggle.com/bminixhofer/aggregated-features-lightgbm\n\nAccording to this notebook, there is a common user in train and test.\nPast user's deal_probability is to predict deal_probability of future user\nIt will be a very useful feature quantity.\n\nDivide test with common users and users not common,\nand trying target_encode!\n\nAlthough it did not work very well in my implementation\nPlease use this idea successfully\n"
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "345524": "https://www.kaggle.com/bminixhofer/aggregated-features-lightgbm\n\nAccording to this notebook, there is a common user in train and test.\nPast user's deal_probability is to predict deal_probability of future user\nIt will be a very useful feature quantity.\n\nDivide test with common users and users not common,\nand trying target_encode!\n\nAlthough it did not work very well in my implementation\nPlease use this idea successfully\n"
  }
}