{
  "id": 58552,
  "title": "Looking for teammate | Bringing text features",
  "url": "/competitions/avito-demand-prediction/discussion/58552",
  "author_name": "Guillaume B",
  "post_date": "2018-06-10T12:34:58.869000",
  "votes": 0,
  "comment_count": 0,
  "views": 0,
  "content": "<p>Hi,</p>\n\n<p>I spent most of my competition working on deep learning models to generate a set of solid features for the text-based columns. I originally took it as a chance to improve my NLP skills but now considering bringing them to a full model to see how they help.</p>\n\n<p>Starting on my own (that's why you won't see submissions), but not sure I'll have enough time to make the most of them. Feel free to reach out if you're a LGBM wizard looking for some additional features !</p>\n\n<p>The way we can make this work is I send a sample with the features for the training set and if we figure something out I'll share the full set of features for the evaluation dataset?</p>\n\n<p>G.</p>",
  "messages": [
    {
      "id": 340832,
      "postDate": "2018-06-10T12:34:58.870Z",
      "content": "<p>Hi,</p>\n\n<p>I spent most of my competition working on deep learning models to generate a set of solid features for the text-based columns. I originally took it as a chance to improve my NLP skills but now considering bringing them to a full model to see how they help.</p>\n\n<p>Starting on my own (that's why you won't see submissions), but not sure I'll have enough time to make the most of them. Feel free to reach out if you're a LGBM wizard looking for some additional features !</p>\n\n<p>The way we can make this work is I send a sample with the features for the training set and if we figure something out I'll share the full set of features for the evaluation dataset?</p>\n\n<p>G.</p>",
      "rawMarkdown": "Hi,\n\nI spent most of my competition working on deep learning models to generate a set of solid features for the text-based columns. I originally took it as a chance to improve my NLP skills but now considering bringing them to a full model to see how they help.\n\nStarting on my own (that's why you won't see submissions), but not sure I'll have enough time to make the most of them. Feel free to reach out if you're a LGBM wizard looking for some additional features !\n\nThe way we can make this work is I send a sample with the features for the training set and if we figure something out I'll share the full set of features for the evaluation dataset?\n\nG."
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "340832": "Hi,\n\nI spent most of my competition working on deep learning models to generate a set of solid features for the text-based columns. I originally took it as a chance to improve my NLP skills but now considering bringing them to a full model to see how they help.\n\nStarting on my own (that's why you won't see submissions), but not sure I'll have enough time to make the most of them. Feel free to reach out if you're a LGBM wizard looking for some additional features !\n\nThe way we can make this work is I send a sample with the features for the training set and if we figure something out I'll share the full set of features for the evaluation dataset?\n\nG."
  }
}