{
  "id": 232683,
  "title": "7th Place Solution",
  "content": "<p>Hi all</p>\n<p>Thanks to the organizers for setting up the competition and many congratulations to the winners!</p>\n<p>It was a great opportunity to experiment with ML techniques on what was a vaguely familiar type of dataset. I looked to learn from the public notebooks of the tabular playground series and started to experiment with AutoML libraries – for the submission I used h2o autoML as it is one of packages installed by kaggle.</p>\n<p>If you are interested, I have tidied up my submission notebook and you can find it here: <br>\n<a href=\"https://www.kaggle.com/bernhardklinger/actuarial-loss-prediction-automl\" target=\"_blank\"></a><a href=\"https://www.kaggle.com/bernhardklinger/actuarial-loss-prediction-automl\" target=\"_blank\">https://www.kaggle.com/bernhardklinger/actuarial-loss-prediction-automl</a><br>\n</p>\n<p>As highlighted in the discussion, the outliers in the dataset have a significant impact on training and validation.  I considered removing the outliers but left them in for the submission and fitted the models to predict the log of the target which seemed to improve the LB score. </p>\n<p>Thanks again to all of you who contributed and shared ideas!</p>",
  "comments": [
    {
      "id": 1287701,
      "author_name": "Jeremy",
      "author_url": "",
      "post_date": "2021-04-29T10:05:30.790000",
      "content": "<p>Hi Bernhard</p>\n<p>Congratulations on finishing in 7th place! 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. 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": 1,
  "messages": [
    {
      "id": 1273989,
      "postDate": "2021-04-14T20:54:05.530Z",
      "content": "<p>Hi all</p>\n<p>Thanks to the organizers for setting up the competition and many congratulations to the winners!</p>\n<p>It was a great opportunity to experiment with ML techniques on what was a vaguely familiar type of dataset. I looked to learn from the public notebooks of the tabular playground series and started to experiment with AutoML libraries – for the submission I used h2o autoML as it is one of packages installed by kaggle.</p>\n<p>If you are interested, I have tidied up my submission notebook and you can find it here: <br>\n<a href=\"https://www.kaggle.com/bernhardklinger/actuarial-loss-prediction-automl\" target=\"_blank\"></a><a href=\"https://www.kaggle.com/bernhardklinger/actuarial-loss-prediction-automl\" target=\"_blank\">https://www.kaggle.com/bernhardklinger/actuarial-loss-prediction-automl</a><br>\n</p>\n<p>As highlighted in the discussion, the outliers in the dataset have a significant impact on training and validation.  I considered removing the outliers but left them in for the submission and fitted the models to predict the log of the target which seemed to improve the LB score. </p>\n<p>Thanks again to all of you who contributed and shared ideas!</p>",
      "rawMarkdown": "Hi all\n\nThanks to the organizers for setting up the competition and many congratulations to the winners!\n\nIt was a great opportunity to experiment with ML techniques on what was a vaguely familiar type of dataset. I looked to learn from the public notebooks of the tabular playground series and started to experiment with AutoML libraries – for the submission I used h2o autoML as it is one of packages installed by kaggle.\n\nIf you are interested, I have tidied up my submission notebook and you can find it here: \n[https://www.kaggle.com/bernhardklinger/actuarial-loss-prediction-automl\n](https://www.kaggle.com/bernhardklinger/actuarial-loss-prediction-automl)\n\nAs highlighted in the discussion, the outliers in the dataset have a significant impact on training and validation.  I considered removing the outliers but left them in for the submission and fitted the models to predict the log of the target which seemed to improve the LB score. \n\nThanks again to all of you who contributed and shared ideas!\n\n",
      "votes": 5
    },
    {
      "id": 1287701,
      "postDate": "2021-04-29T10:05:30.790Z",
      "content": "<p>Hi Bernhard</p>\n<p>Congratulations on finishing in 7th place! 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. 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 Bernhard\n\nCongratulations on finishing in 7th place! I am Jeremy, one of the organisers of the competition.\n\nWe would very much like to discuss your modelling approach and insights. If 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": "2026-10-19T19:14:20Z",
  "competition_id": 24764,
  "competition_slug": "actuarial-loss-estimation",
  "team_id": 6328453,
  "solution_url": "/competitions/actuarial-loss-estimation/writeups/bernhard-klinger-7th-place-solution"
}