{
  "fetched_at": "2026-10-19T10:16:23Z",
  "source_url": "https://www.kaggle.com/competitions/en553803-financial-computing-workshop-2021/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## 10k_filings_train.csv\n\nThis is the train set. You will train your model of choice on this data. You can split this train set into a train and validation for hyperparameter tuning. \n\nThe column you want to predict is the `label` column. There are 9 unique sectors, so this is a multiclass classification problem. The company sectors were identified from the SEC website. While there are many more detailed sectors (under \"industry\" column), in this task you only have to predict the high-level sector group.\n\n<strong> Only use the body of the 10K for features </strong>.\n\n## 10k_filings_test_wo_labels.csv\n\nTest set. The labels are omitted. Only submit your model's predicted sector for the test set.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>You learned about text representation and machine learning, and now it is time to put these concepts together. </p>\n\n<p>We have a set of 10k's and their respective sector labels. The goal is to train a model that can predict the sector of a company using only the text from its 10k filing.</p>\n\n<p>Click on the \"Data\" tab to access the train and test set. You only submit your predictions on the <strong>test set</strong>.</p>\n\n<hr>\n\n<h2>Evaluation</h2>\n<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\n<hr>\n<h2>Submission Format</h2>\n<p><strong>For every company in the dataset</strong>, submission files should contain two columns: id and label. The id is the provided id in the test file (e.g. 935036-2017-1) and label is a string containing the predicted sector (e.g. Mining).\n\n</p><p>The file should contain a header and have the following format:</p>\n<pre>id,label<br>935036-2017-1,Mining<br></pre>\n\n<hr>\n\n<h2>Example</h2>\nBelow is an example submission in a Kaggle \"kernel\". You may write your code on Kaggle, on your local machine in a script, or on your local machine in a notebook. <strong> You will submit your code in PDF/HTML form on Piazza.</strong>\n\n<a href=\"https://www.kaggle.com/alexandradelucia/randomguesser\">RandomGuesser Kernel</a>\n\n<h2>Acknowledgements</h2>\n<p>We thank Professors John Miller and Dan Naiman for the opportunity to teach this class. And we thank the students for a great class!</p>",
      "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
    }
  ]
}