{
  "id": 287778,
  "title": "Top 1 Solution",
  "content": "<p>Hola/Hello everybody,</p>\n<p>First of all, thank you for hosting the competition, was super fun to compete.</p>\n<p>There is no magic int terms of what I have done to win this, I have tried many algorithms and the one that worked the best was XGBoost.</p>\n<p>The solution: 5 folds XGBoost with tuned up parameters -&gt; take the ensemble mean of all 5 predictions.</p>\n<p>I saw a lot of people dropping the features that were missing numbers, that is a wrong way to deal with it in this competition. XGBoost actually allows you to take in the NaN.</p>\n<p>Best regards and congratulations to all the participants !<br>\nAs long as you learned something new, you are a winner.</p>",
  "comments": [],
  "comment_count": 0,
  "messages": [
    {
      "id": 1583084,
      "postDate": "2021-11-15T14:17:45.110Z",
      "content": "<p>Hola/Hello everybody,</p>\n<p>First of all, thank you for hosting the competition, was super fun to compete.</p>\n<p>There is no magic int terms of what I have done to win this, I have tried many algorithms and the one that worked the best was XGBoost.</p>\n<p>The solution: 5 folds XGBoost with tuned up parameters -&gt; take the ensemble mean of all 5 predictions.</p>\n<p>I saw a lot of people dropping the features that were missing numbers, that is a wrong way to deal with it in this competition. XGBoost actually allows you to take in the NaN.</p>\n<p>Best regards and congratulations to all the participants !<br>\nAs long as you learned something new, you are a winner.</p>",
      "rawMarkdown": "Hola/Hello everybody,\n\nFirst of all, thank you for hosting the competition, was super fun to compete.\n\nThere is no magic int terms of what I have done to win this, I have tried many algorithms and the one that worked the best was XGBoost.\n\nThe solution: 5 folds XGBoost with tuned up parameters -> take the ensemble mean of all 5 predictions.\n\nI saw a lot of people dropping the features that were missing numbers, that is a wrong way to deal with it in this competition. XGBoost actually allows you to take in the NaN.\n\nBest regards and congratulations to all the participants !\nAs long as you learned something new, you are a winner.",
      "votes": 8
    }
  ],
  "complete": true,
  "source": "live",
  "fetched_at": "2026-10-19T19:52:29Z",
  "competition_id": 32437,
  "competition_slug": "gmsc-thebridge-dsft2109",
  "team_id": 7715025,
  "solution_url": "/competitions/gmsc-thebridge-dsft2109/writeups/alin-cijov-top-1-solution"
}