{
  "fetched_at": "2026-10-24T10:37:51Z",
  "source_url": "https://www.kaggle.com/competitions/allianzconv/data",
  "pages": [
    {
      "name": "rules",
      "content": "    <h3>Be creative !</h3>\n<p>The purpose of this competition is to give you the opportunity to learn Machine learning while using your creative mind. The target is simple, reach the best AUC applying whichever tool (SAS, R, python, etc.), strategy and statistical method you want. </p>\n\n<h3>One account per participant</h3>\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n\n    <h3>No private sharing outside teams</h3>\n    <p>\n        Privately sharing code or data outside of teams is not permitted.\n        It's okay to share code if made available to all participants on the forums.\n    </p>\n\n    <h3>Team Mergers</h3>\n    <p>Team mergers are not allowed in this competition.</p>\n\n    <h3>Team Limits</h3>\n    <p>There is a maximum team size of 4. Teams are allocated based on previous polls and information about your experience in machine learning. You cannot change your team. We strongly encourage teams to work altogether as the the prize goes to the winning team of 3.</p>\n\n    <h3>Submission Limits</h3>\n    <p>You may submit a maximum of 5 entries per day.</p>\n    <p>You may select up to 2 final submissions for judging.</p>\n\n    <h3>Competition Timeline</h3>\n    <p>Start Date: <strong>17/12/2018</strong></p>\n    <p>End Date: <strong>15/02/2019</strong></p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>This dataset represents the activity of a large number of customers who are interested in buying policies from Allianz. Each Each observation corresponds to a potential customer and the feature NEWBUS indicates whether the customer purchased a policy.</p>\n\n<p>  The new datasets is taking into account the fact that few factors were self explanatory and were then suppressed </p>\n\n<p>The provided dataset is SAF2 and provide a rich representation of the prospective customer and policy. They include specific coverage information, personal information, property information, and geographic information. Your task is to predict NEWBUS for each Quote in the test set.</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the test set</li>\n<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n\n<h2>Data location</h2>\n<p>Data are available in the following folder : N:\\Resources\\Data Science\\Kaggle\\Conversion_NEW_VERSION </p>\n\n<h2>Data fields</h2>\n<ul>\n<li><strong>UNIQUE_ID</strong> - an anonymous id unique to a given customer</li>\n<li><strong>CLUSTER_[CTS/BLD]_</strong> - geographical clusters of classifier per product per risk</li>\n<li><strong>QUOTE_PREMIUM</strong> - the quote premium</li>\n<li><strong>START_DATE</strong> - Inception date</li>\n<li><strong>DIST2</strong> - Distribution channel</li>\n<li><strong>CONS_TYPE_DESC</strong> - Construction type</li>\n<li><strong>ROOF_TYPE_DESC</strong> - Roof type</li>\n<li><strong>OCC_TYPE</strong> - Occupancy type</li>\n<li><strong>H_BUILDING_SUMINSURED</strong> - Building sum insured</li>\n<li><strong>TOT_SUM_INS</strong> - Total sum insured at policy level</li>\n<li><strong>YEAR_CONS</strong> - Building year of construction</li>\n<li><strong>GEO_[...]</strong> - Geographical census information</li>\n<li><strong>AGE_OWN</strong> - Owner's age</li>\n<li><strong>ICA_ZONE</strong> - Geographical zones of Australia used in weather modelling. Equivalent to Cresta zones </li>\n<li><strong>AFFORDABILITY</strong> - ratio between premium and average income per geographical zone</li>\n\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>Before asking someone on a date or skydiving, it's important to know your likelihood of success. The same goes for quoting home insurance prices to a potential customer. With a strategy aiming at applying new processes, Allianz looks at applying a dynamic conversion rate model that can give them confidence a quoted price will lead to a purchase. </p>\n\n<img src=\"https://i.ytimg.com/vi/xrv4Pcp-s6E/maxresdefault.jpg\"  width=\"300\" style= \"float: right;\" alt=\"Shipping\">\n\n<p>Using SAF2 database of information on customer and geographical information including property and coverage information, Allianz is challenging you to predict which customers will purchase a given quote. Accurately predicting conversion would help Allianz better understand the impact of proposed pricing changes and maintain an ideal portfolio of customer segments. </p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://www.medcalc.org/manual/roc-curves.php\"> AUC</a>. Submissions are evaluated on area under the ROC curve between the predicted probability and the observed target. </p>\n\n<h2> Submission file </h2>\nFor each Quote in the test set, you must predict a probability for NEWBUS. The file should contain a header and have the same format than sample_submission.csv",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}