{
  "id": 232250,
  "title": "9th place solution",
  "content": "<p>Hello,</p>\n<p>It was my first competition here in kaggle. I discovered most of the techniques that I use a few weeks before the competition so I can't complain about the ranking x) (I'm even surprised).</p>\n<p>Regarding my solution, I did feature engineering, <strong>MixedPCA</strong> on some specific features, created hundreds of dummies to model the so-called ClaimDescription variable based on word frequency (I did a large part manually : selecting words, combination of words and so on), I also saw that there were patterns at the end of some sentences but had trouble modeling them. I then tried a few boosting methods (<strong>GBM</strong> and <strong>Xgboost</strong> mainly) using the h2o package and neural network models and a belnding after that. <br>\nI also learned a lot from the competition public notebooks and tried them after changing their features engineering part.</p>\n<p>Happy to found such an amazing community of actuaries here in kaggle ! 😃</p>",
  "comments": [
    {
      "id": 1271940,
      "author_name": "aldparis",
      "author_url": "",
      "post_date": "2021-04-13T05:00:33.430000",
      "content": "<p>Congratulation ! Thanks for sharing ! And welcome to kaggle !</p>",
      "votes": 1,
      "replies": []
    },
    {
      "id": 1271815,
      "author_name": "Issac Lee",
      "author_url": "",
      "post_date": "2021-04-12T23:58:09.840000",
      "content": "<p>Congratulation!! Thanks for sharing! Could you share about Mixed PCA on what features and why? :)</p>",
      "votes": 2,
      "replies": []
    },
    {
      "id": 1322979,
      "author_name": "Jeremy",
      "author_url": "",
      "post_date": "2021-05-25T20:56:27.910000",
      "content": "<p>Hi Mohammed-Amine</p>\n<p>Thank you for participating in the competition and sharing your approach.</p>\n<p>I am Jeremy, one of the organisers of the competition.</p>\n<p>We would very much like to discuss your modelling approach and insights in more detail. (<a href=\"https://www.kaggle.com/c/actuarial-loss-estimation/discussion/234916\" target=\"_blank\">https://www.kaggle.com/c/actuarial-loss-estimation/discussion/234916</a>)</p>\n<p>If you are happy to get in touch, please drop me an email at jeremwang@deloitte.co.uk.</p>\n<p>Thanks<br>\nJeremy</p>",
      "votes": 0,
      "replies": []
    }
  ],
  "comment_count": 3,
  "messages": [
    {
      "id": 1271723,
      "postDate": "2021-04-12T20:54:50.033Z",
      "content": "<p>Hello,</p>\n<p>It was my first competition here in kaggle. I discovered most of the techniques that I use a few weeks before the competition so I can't complain about the ranking x) (I'm even surprised).</p>\n<p>Regarding my solution, I did feature engineering, <strong>MixedPCA</strong> on some specific features, created hundreds of dummies to model the so-called ClaimDescription variable based on word frequency (I did a large part manually : selecting words, combination of words and so on), I also saw that there were patterns at the end of some sentences but had trouble modeling them. I then tried a few boosting methods (<strong>GBM</strong> and <strong>Xgboost</strong> mainly) using the h2o package and neural network models and a belnding after that. <br>\nI also learned a lot from the competition public notebooks and tried them after changing their features engineering part.</p>\n<p>Happy to found such an amazing community of actuaries here in kaggle ! 😃</p>",
      "rawMarkdown": "Hello,\n\nIt was my first competition here in kaggle. I discovered most of the techniques that I use a few weeks before the competition so I can't complain about the ranking x) (I'm even surprised).\n\nRegarding my solution, I did feature engineering, **MixedPCA** on some specific features, created hundreds of dummies to model the so-called ClaimDescription variable based on word frequency (I did a large part manually : selecting words, combination of words and so on), I also saw that there were patterns at the end of some sentences but had trouble modeling them. I then tried a few boosting methods (**GBM** and **Xgboost** mainly) using the h2o package and neural network models and a belnding after that. \nI also learned a lot from the competition public notebooks and tried them after changing their features engineering part.\n\nHappy to found such an amazing community of actuaries here in kaggle ! 😃\n",
      "votes": 9
    },
    {
      "id": 1271940,
      "postDate": "2021-04-13T05:00:33.430Z",
      "content": "<p>Congratulation ! Thanks for sharing ! And welcome to kaggle !</p>",
      "rawMarkdown": "Congratulation ! Thanks for sharing ! And welcome to kaggle !",
      "votes": 1
    },
    {
      "id": 1271815,
      "postDate": "2021-04-12T23:58:09.840Z",
      "content": "<p>Congratulation!! Thanks for sharing! Could you share about Mixed PCA on what features and why? :)</p>",
      "rawMarkdown": "Congratulation!! Thanks for sharing! Could you share about Mixed PCA on what features and why? :)",
      "votes": 2
    },
    {
      "id": 1322979,
      "postDate": "2021-05-25T20:56:27.910Z",
      "content": "<p>Hi Mohammed-Amine</p>\n<p>Thank you for participating in the competition and sharing your approach.</p>\n<p>I am Jeremy, one of the organisers of the competition.</p>\n<p>We would very much like to discuss your modelling approach and insights in more detail. (<a href=\"https://www.kaggle.com/c/actuarial-loss-estimation/discussion/234916\" target=\"_blank\">https://www.kaggle.com/c/actuarial-loss-estimation/discussion/234916</a>)</p>\n<p>If you are happy to get in touch, please drop me an email at jeremwang@deloitte.co.uk.</p>\n<p>Thanks<br>\nJeremy</p>",
      "rawMarkdown": "Hi Mohammed-Amine\n\nThank you for participating in the competition and sharing your approach.\n\nI am Jeremy, one of the organisers of the competition.\n\nWe would very much like to discuss your modelling approach and insights in more detail. (https://www.kaggle.com/c/actuarial-loss-estimation/discussion/234916)\n\nIf you are happy to get in touch, please drop me an email at jeremwang@deloitte.co.uk.\n\nThanks\nJeremy"
    }
  ],
  "complete": true,
  "source": "live",
  "fetched_at": "2026-10-19T19:14:42Z",
  "competition_id": 24764,
  "competition_slug": "actuarial-loss-estimation",
  "team_id": 6040994,
  "solution_url": "/competitions/actuarial-loss-estimation/writeups/skoubani-mohammed-amine-9th-place-solution"
}