{
  "fetched_at": "2026-10-19T16:43:38Z",
  "source_url": "https://www.kaggle.com/competitions/click-through-rate-prediction-tdvi-2024/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train</strong> - The training set (‘ctr_n.csv‘ files) consists of a portion of Jampp’s click-through data over a period of 7 days, not necessarily chronologically ordered (however a time column is provided).</li>\n<li><strong>test</strong> - The test set (‘ctr_test.csv‘) consists of a sample of Jampp’s traffic on the week following the training period (computed in the same way as the training set). Note: it isn’t labeled (i.e no Label column) since it is your job to predict these outcomes. It\ndoes include an id column to be used for results submission.</li>\n<li><strong>sample_submission.csv</strong> - A sample submission file in the correct format</li>\n\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li><strong>Label</strong> - target variable that indicates if the ad was clicked (1) or not (0).\n<li><strong>action_categorical_0</strong> - business unit id. 1st level. These ids have a one to many relationship: a 1st level id can have many 2nd level, but a 2nd level can have only a single 1st level parent id.\n<li><strong>action_categorical_1</strong> - business unit id. 2nd level\n<li><strong>action_categorical_2</strong> - business unit id. 3rd level\n<li><strong>action_categorical_3</strong> - business unit id. 4th level\n<li><strong>action_categorical_4</strong> - business unit id. 5th level\n<li><strong>action_categorical_5</strong> - a categorical variable\n<li><strong>action_categorical_6</strong> - a categorical variable\n<li><strong>action_categorical_7</strong> - a categorical variable\n<li><strong>action_list_0</strong> - a list of categories related to the action\n<li><strong>action_list_1</strong> - a list of entity ids related to the action\n<li><strong>action_list_2</strong> - a list of entity ids related to the action\n<li><strong>auction_time</strong> - the time in which the auction took place. Format is unix time (a.k.a. epoch time).\n<li><strong>auction_age</strong> - the user’s age\n<li><strong>auction_bidfloor</strong> - bidfloor (the minimum value you can bid for)\n<li><strong>auction_boolean_0</strong> - a boolean variable regarding an attribute of the auction\n<li><strong>auction_boolean_1</strong> - a boolean variable regarding an attribute of the auction\n<li><strong>auction_boolean_2</strong> - a boolean variable regarding an attribute of the auction\n<li><strong>auction_categorical_0</strong> - an entity id related to a component of the auction\n<li><strong>auction_categorical_1</strong> - an entity id related to a component of the auction\n<li><strong>auction_categorical_2</strong> - a categorical variable\n<li><strong>auction_categorical_3</strong> - a categorical variable\n<li><strong>auction_categorical_4</strong> - a categorical variable\n<li><strong>auction_categorical_5</strong> - a categorical variable\n<li><strong>auction_categorical_6</strong> - a categorical variable\n<li><strong>auction_categorical_7</strong> - an entity id related to a component of the auction\n<li><strong>auction_categorical_8</strong> - an entity id related to a component of the auction\n<li><strong>auction_categorical_9</strong> - an entity id related to a component of the auction\n<li><strong>auction_categorical_10</strong> - a categorical variable\n<li><strong>auction_categorical_11</strong> - an entity id related to a component of the auction\n<li><strong>auction_categorical_12</strong> - a categorical variable\n<li><strong>auction_list_0</strong> - a list of categories related to the auction\n<li><strong>creative_categorical_0</strong> - business unit id\n<li><strong>creative_categorical_1</strong> - a categorical variable\n<li><strong>creative_categorical_10</strong> - a categorical variable\n<li><strong>creative_categorical_11</strong> - a categorical variable\n<li><strong>creative_categorical_12</strong> - a categorical variable\n<li><strong>creative_categorical_2</strong> - a categorical variable\n<li><strong>creative_categorical_3</strong> - a categorical variable\n<li><strong>creative_categorical_4</strong> - a categorical variable\n<li><strong>creative_categorical_5</strong> - business unit id\n<li><strong>creative_categorical_6</strong> - a categorical variable\n<li><strong>creative_categorical_7</strong> - a categorical variable\n<li><strong>creative_categorical_8</strong> - a categorical variable\n<li><strong>creative_categorical_9</strong> - a categorical variable\n<li><strong>creative_height</strong> - the creative’s height (in pixels)\n<li><strong>creative_width</strong> - the creative’s width (in pixels)\n<li><strong>device_id</strong> - the device id. This is a unique identifier for a device (or close to unique)\n<li><strong>device_id_type</strong> - the type of device id (there are many types, also a device can have many different types, with a different id for each of them)\n<li><strong>gender</strong> - gender\n<li><strong>has_video</strong> - a boolean value indicating if the banner contains a video.\n<li><strong>timezone_offset</strong> - timezone offset in hours based on the auction’s country and region.<li>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is AUC-ROC.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "We were very lucky in being able to run our course competition with real data. You will have to predict clicks in mobile advertising.\n\nIn display and mobile advertising, the most relevant technical development in recent years is the growth of Real-Time Bidding (RTB). Billions of display ad impressions are purchased on a daily basis through a public auction hosted by RTB exchanges. The auction is per impression and the process usually occurs less than 100 milliseconds before the ad is placed. In this context, demand side platforms (DSPs) were created to help advertisers manage their campaigns and optimise their real-time bidding activities. One of their main tasks is to predict the click-through rate (CTR) for ads and calculate the bid price according to the estimated CTR.\n\nFor this challenge, Jampp, one of the key players in the mobile adtech industry, has provided a week’s worth of data to build and test models predicting CTR.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}