{
  "id": 22818,
  "title": "Team up and try to win?",
  "url": "/competitions/grupo-bimbo-inventory-demand/discussion/22818",
  "author_name": "",
  "post_date": "2016-08-11T21:06:54.947Z",
  "votes": 1,
  "comment_count": 2,
  "views": 801,
  "content": "<p>Hi,</p>\n\n<p>I am asking if anyone who is in top 3% or so want(s) to team up with me. I have reached 0.436xxx on LB about 50 days ago at which point I started to focus mostly on developing validation strategies. I wasn't not quite successful in developing new features, because I always could observe some kinda of overfitting by adding features. With a proper validation strategy and some merged features, I think we could have a reasonable chance ending up in top3. </p>\n\n<p>I am also new to Kaggle (actually my first competition). So it would be great if some more experienced one would teach me on ensembling and featuring. I am speaking Chinese and English. Thanks!</p>\n\n<p>BTW. I have access to a computing cluster which can be useful in running many large models (such as XGBs).</p>\n\n<p>Please contact ASAP.\nEMAIL: yelpoo [at] gmail [dot] com</p>\n\n<p>Jianbo</p>",
  "messages": [
    {
      "id": "130986",
      "postDate": "08/11/2016 21:06:54",
      "content": "<p>Hi,</p>\n\n<p>I am asking if anyone who is in top 3% or so want(s) to team up with me. I have reached 0.436xxx on LB about 50 days ago at which point I started to focus mostly on developing validation strategies. I wasn't not quite successful in developing new features, because I always could observe some kinda of overfitting by adding features. With a proper validation strategy and some merged features, I think we could have a reasonable chance ending up in top3. </p>\n\n<p>I am also new to Kaggle (actually my first competition). So it would be great if some more experienced one would teach me on ensembling and featuring. I am speaking Chinese and English. Thanks!</p>\n\n<p>BTW. I have access to a computing cluster which can be useful in running many large models (such as XGBs).</p>\n\n<p>Please contact ASAP.\nEMAIL: yelpoo [at] gmail [dot] com</p>\n\n<p>Jianbo</p>",
      "rawMarkdown": "Hi,\r\n\r\nI am asking if anyone who is in top 3% or so want(s) to team up with me. I have reached 0.436xxx on LB about 50 days ago at which point I started to focus mostly on developing validation strategies. I wasn't not quite successful in developing new features, because I always could observe some kinda of overfitting by adding features. With a proper validation strategy and some merged features, I think we could have a reasonable chance ending up in top3. \r\n\r\nI am also new to Kaggle (actually my first competition). So it would be great if some more experienced one would teach me on ensembling and featuring. I am speaking Chinese and English. Thanks!\r\n\r\nBTW. I have access to a computing cluster which can be useful in running many large models (such as XGBs).\r\n\r\nPlease contact ASAP.\r\nEMAIL: yelpoo [at] gmail [dot] com\r\n\r\nJianbo",
      "votes": null
    },
    {
      "id": "131806",
      "postDate": "08/19/2016 18:58:37",
      "content": "<p>What computing clustering service are you using? Are you using R or Python?</p>",
      "rawMarkdown": "What computing clustering service are you using? Are you using R or Python?",
      "votes": null
    },
    {
      "id": "132035",
      "postDate": "08/21/2016 22:26:07",
      "content": "<p>[quote=Ying Haw Lee;131806]</p>\n\n<p>What computing clustering service are you using? Are you using R or Python?</p>\n\n<p>[/quote]</p>\n\n<p>I use C++ for feature engineering. -Jianbo</p>",
      "rawMarkdown": "[quote=Ying Haw Lee;131806]\r\n\r\nWhat computing clustering service are you using? Are you using R or Python?\r\n\r\n[/quote]\r\n\r\nI use C++ for feature engineering. -Jianbo",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 131806,
      "author_name": "yinghawl",
      "author_url": "",
      "post_date": "08/19/2016 18:58:37",
      "content": "<p>What computing clustering service are you using? Are you using R or Python?</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 132035,
      "author_name": "amazingbob",
      "author_url": "",
      "post_date": "08/21/2016 22:26:07",
      "content": "<p>[quote=Ying Haw Lee;131806]</p>\n\n<p>What computing clustering service are you using? Are you using R or Python?</p>\n\n<p>[/quote]</p>\n\n<p>I use C++ for feature engineering. -Jianbo</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "130986": "Hi,\r\n\r\nI am asking if anyone who is in top 3% or so want(s) to team up with me. I have reached 0.436xxx on LB about 50 days ago at which point I started to focus mostly on developing validation strategies. I wasn't not quite successful in developing new features, because I always could observe some kinda of overfitting by adding features. With a proper validation strategy and some merged features, I think we could have a reasonable chance ending up in top3. \r\n\r\nI am also new to Kaggle (actually my first competition). So it would be great if some more experienced one would teach me on ensembling and featuring. I am speaking Chinese and English. Thanks!\r\n\r\nBTW. I have access to a computing cluster which can be useful in running many large models (such as XGBs).\r\n\r\nPlease contact ASAP.\r\nEMAIL: yelpoo [at] gmail [dot] com\r\n\r\nJianbo",
    "131806": "What computing clustering service are you using? Are you using R or Python?",
    "132035": "[quote=Ying Haw Lee;131806]\r\n\r\nWhat computing clustering service are you using? Are you using R or Python?\r\n\r\n[/quote]\r\n\r\nI use C++ for feature engineering. -Jianbo"
  },
  "source": "meta"
}