{
  "id": 375192,
  "title": "💡 How to ensemble predictions and improve your score?",
  "url": "/competitions/otto-recommender-system/discussion/375192",
  "author_name": "Radek Osmulski",
  "post_date": "2022-12-30T21:32:49.996000",
  "votes": 10,
  "comment_count": 0,
  "views": 0,
  "content": "<p>With just a few more days to go in the competition, it is time to start thinking about your final submission!</p>\n<p>One great way to improve your score is to ensemble predictions, but in a competition like this doing so might not be that straightforward.</p>\n<p>That is why I prepared this notebook:<br>\n<a href=\"https://www.kaggle.com/code/radek1/2-methods-how-to-ensemble-predictions\" target=\"_blank\">💡 [2 methods] How-to ensemble predictions 🏅🏅🏅</a></p>\n<p>In it, I ensemble the predictions using two approaches:</p>\n<ul>\n<li>vote ensembling</li>\n<li>weighted vote ensembling</li>\n</ul>\n<p>For these methods to work, you need at least 3 submissions!</p>\n<p>If you would have any questions on how all of this works, please feel free to ask here or on the notebook itself!</p>\n<p>Thanks for reading, hope this technique can be useful to you, and best of luck in the competition! 🍀🤞</p>",
  "messages": [
    {
      "id": 2081160,
      "postDate": "2022-12-30T21:32:49.997Z",
      "content": "<p>With just a few more days to go in the competition, it is time to start thinking about your final submission!</p>\n<p>One great way to improve your score is to ensemble predictions, but in a competition like this doing so might not be that straightforward.</p>\n<p>That is why I prepared this notebook:<br>\n<a href=\"https://www.kaggle.com/code/radek1/2-methods-how-to-ensemble-predictions\" target=\"_blank\">💡 [2 methods] How-to ensemble predictions 🏅🏅🏅</a></p>\n<p>In it, I ensemble the predictions using two approaches:</p>\n<ul>\n<li>vote ensembling</li>\n<li>weighted vote ensembling</li>\n</ul>\n<p>For these methods to work, you need at least 3 submissions!</p>\n<p>If you would have any questions on how all of this works, please feel free to ask here or on the notebook itself!</p>\n<p>Thanks for reading, hope this technique can be useful to you, and best of luck in the competition! 🍀🤞</p>",
      "rawMarkdown": "With just a few more days to go in the competition, it is time to start thinking about your final submission!\n\nOne great way to improve your score is to ensemble predictions, but in a competition like this doing so might not be that straightforward.\n\nThat is why I prepared this notebook:\n[💡 [2 methods] How-to ensemble predictions 🏅🏅🏅](https://www.kaggle.com/code/radek1/2-methods-how-to-ensemble-predictions)\n\nIn it, I ensemble the predictions using two approaches:\n* vote ensembling\n* weighted vote ensembling\n\nFor these methods to work, you need at least 3 submissions!\n\nIf you would have any questions on how all of this works, please feel free to ask here or on the notebook itself!\n\nThanks for reading, hope this technique can be useful to you, and best of luck in the competition! 🍀🤞",
      "votes": 10
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "2081160": "With just a few more days to go in the competition, it is time to start thinking about your final submission!\n\nOne great way to improve your score is to ensemble predictions, but in a competition like this doing so might not be that straightforward.\n\nThat is why I prepared this notebook:\n[💡 [2 methods] How-to ensemble predictions 🏅🏅🏅](https://www.kaggle.com/code/radek1/2-methods-how-to-ensemble-predictions)\n\nIn it, I ensemble the predictions using two approaches:\n* vote ensembling\n* weighted vote ensembling\n\nFor these methods to work, you need at least 3 submissions!\n\nIf you would have any questions on how all of this works, please feel free to ask here or on the notebook itself!\n\nThanks for reading, hope this technique can be useful to you, and best of luck in the competition! 🍀🤞"
  }
}