{
  "id": 370590,
  "title": "#1 Solution ",
  "content": "<p>Sorry for the late post.</p>\n<ul>\n<li><p>Tried a few approaches but found that light gradient boosted models (lightgbm) worked the best.</p></li>\n<li><p>In this solution, I show lightgbm modeling over full training data set as lightgbm tends to do well even with low information data.</p></li>\n<li><p>Data was trained using a 80/20 training/validation split to find optimal parameters for model. The parameters was optimized utilizing over 1000 iterations of random selection of 6 different parameters</p></li>\n<li><p>Afterwards, model was trained on full data set to predict on test data set</p></li>\n</ul>\n<p>code can be found <a href=\"https://www.kaggle.com/code/paulyy27/tfug-diabetes-prediction-using-lightgbm/\" target=\"_blank\">here</a></p>",
  "comments": [
    {
      "id": 2056041,
      "author_name": "Paul",
      "author_url": "",
      "post_date": "2022-12-05T17:13:12.597000",
      "content": "<p>Thank you! I have emailed you. And thank you for the great competition </p>",
      "votes": 0,
      "replies": []
    },
    {
      "id": 2055758,
      "author_name": "AashiDutt",
      "author_url": "",
      "post_date": "2022-12-05T12:33:16.393000",
      "content": "<p>Congratulations Paul🎉 and thank you for sharing your winning approach with everyone. <br>\nWe look forward to sharing your prize soon and may you win more of them. Please share your email with us at - <a>tfugchd@gmail.com</a></p>",
      "votes": 0,
      "replies": []
    }
  ],
  "comment_count": 2,
  "messages": [
    {
      "id": 2055740,
      "postDate": "2022-12-05T11:39:51.710Z",
      "content": "<p>Sorry for the late post.</p>\n<ul>\n<li><p>Tried a few approaches but found that light gradient boosted models (lightgbm) worked the best.</p></li>\n<li><p>In this solution, I show lightgbm modeling over full training data set as lightgbm tends to do well even with low information data.</p></li>\n<li><p>Data was trained using a 80/20 training/validation split to find optimal parameters for model. The parameters was optimized utilizing over 1000 iterations of random selection of 6 different parameters</p></li>\n<li><p>Afterwards, model was trained on full data set to predict on test data set</p></li>\n</ul>\n<p>code can be found <a href=\"https://www.kaggle.com/code/paulyy27/tfug-diabetes-prediction-using-lightgbm/\" target=\"_blank\">here</a></p>",
      "rawMarkdown": "Sorry for the late post.\n\n- Tried a few approaches but found that light gradient boosted models (lightgbm) worked the best.\n- In this solution, I show lightgbm modeling over full training data set as lightgbm tends to do well even with low information data.\n\n- Data was trained using a 80/20 training/validation split to find optimal parameters for model. The parameters was optimized utilizing over 1000 iterations of random selection of 6 different parameters\n- Afterwards, model was trained on full data set to predict on test data set\n\ncode can be found [here](https://www.kaggle.com/code/paulyy27/tfug-diabetes-prediction-using-lightgbm/)\n",
      "votes": 1
    },
    {
      "id": 2056041,
      "postDate": "2022-12-05T17:13:12.597Z",
      "content": "<p>Thank you! I have emailed you. And thank you for the great competition </p>",
      "rawMarkdown": "Thank you! I have emailed you. And thank you for the great competition "
    },
    {
      "id": 2055758,
      "postDate": "2022-12-05T12:33:16.393Z",
      "content": "<p>Congratulations Paul🎉 and thank you for sharing your winning approach with everyone. <br>\nWe look forward to sharing your prize soon and may you win more of them. Please share your email with us at - <a>tfugchd@gmail.com</a></p>",
      "rawMarkdown": "Congratulations Paul🎉 and thank you for sharing your winning approach with everyone. \nWe look forward to sharing your prize soon and may you win more of them. Please share your email with us at - tfugchd@gmail.com"
    }
  ],
  "complete": true,
  "source": "live",
  "fetched_at": "2026-10-19T20:45:39Z",
  "competition_id": 42910,
  "competition_slug": "diabetes-prediction-competitiontfug-chd-nov-2022",
  "team_id": 9533596,
  "solution_url": "/competitions/diabetes-prediction-competitiontfug-chd-nov-2022/writeups/paul-1-solution"
}