{
  "fetched_at": "2026-10-19T14:07:58Z",
  "source_url": "https://www.kaggle.com/competitions/cs98x-dl-task2-contract-clasification/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>Below are the descriptions of the training and test data. Your task is to predict the field called \"label\" which is a binary string that represents the 9 classes: \"General\", \"Defence\", \"Education & Culture\", \"Energy & Environment\",\" Health & Care\", \"Infrastructure & Construction\", \"Professional Services\", \"Technology & Communications\", \"Transport & Logistics\".</p>\n\n<p>The training data contain the classes in a field called \"category\"- but the test data does not!</p>\n\n\n<h2>File descriptions</h2>\n<ul>\n<li><strong>contacts-train.csv</strong> - the training set</li>\n<li><strong>contracts-test.csv</strong> - the test set</li>\n<li><strong>contracts-sample-submission_1.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n<h2>Data fields</h2>\n<ul>\n<li>'publication_date' - the date the contract was published</li>\n<li>'contract_type' - notice or award</li>\n <li>'nature_of_contract' - supplies, works, or services</li>\n <li>'country_code' - two letter to represent the country that issued the tender</li>\n<li>'country_name' - country name </li>\n<li>'sector' - private or public sector tender</li>\n<li>'category' - a list of the categories the contract belongs\n<li>'value' - value of the tender, if available</li>\n'<li>title' - title of the tender</li>\n<li>'description’- description of the tender</li>\n<li>'awarding_authority' - authority that will award the contract</li>\n<li>'complete_entry' - the complete text associated with the tender</li>\n\n<li>'label' - the classes that the document belongs to (given fields, \"General\", \"Defence\",\"Education & Culture\",\"Energy & Environment\",\"Health & Care\",\"Infrastructure & Construction\",\"Professional Services\",\"Technology & Communications\",\"Transport & Logistics”</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is a multi-class classification problem where given the descriptors of a contract document where the task is to predict which classes it is associated with i.e. Defence, Health, Environment, etc.. There are 9 classes associated with each contract. \n\nDue to the limitations of Kaggle you need to generate a binary label to represent whether the class is present or not. See the data section for an overview of the classes and a sample submission file.",
      "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.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\n<h2>Submission Format</h2>\n<p><strong>For every document</strong>, the submission files should contain two columns: dicid, and label, where the label is binary string of length nine. See sample submission in the data section.\n.</p>\n",
      "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!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}