{
  "fetched_at": "2026-10-19T13:16:59Z",
  "source_url": "https://www.kaggle.com/competitions/2020-spring-cse6250-bdh/data",
  "pages": [
    {
      "name": "rules",
      "content": "<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<p>Sign up with your <strong>georgia tech</strong> account including username/email and your name for the convenience of grading work please.</p>\n<h3>No private sharing outside teams</h3>\n<p>Privately sharing code or data outside of teams is not permitted. </p>\n<p><strong>System will only record your last submission as competition result</strong></p>\n<h3>Competition Timeline</h3>\n<p>Start Date: <strong>1/7/2019 11:00 AM EST</strong></p>\n<p>Merger Deadline: <strong>None</strong></p>\n<p>Entry Deadline: <strong>None</strong></p>\n<p>End Date: <strong>1/20/2019 7:00 AM EST</strong></p>\n\n<p><strong>Attention: kaggle do not allow late submission, so grace period is not unaccepted after the deadline. If you want to get this part of score, please make sure you submit it in time.</strong></p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set, same as your HW1 data</li>\n<li><strong>test.csv</strong> - the test set, same as your HW1 data</li>\n<li><strong>sampleSubmission.csv</strong> - please see overview description</li>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Description</h2>\n<p>A gatech.edu email address is required to participate. In the homework1.pdf, we ask you to apply the machine learning to predict mortality of patients and you choose your own prediction model in Section 4.3. In this challenge, you will submit your prediction to compete with your fellow classmates. Submissions should be a csv file with two columns labeled \"patient_id\" and \"label\"; including the header they should be 634 rows. Consider using utils.generate_submission(). After you submit, your accuracy on 50% of the test dataset will be visible to the class on the public leaderboard. You can use this accuracy as a sanity check to make sure your classifier is performing as intended and improve your model further. Once the competition ends, your response will be evaluated on the other 50% of the test data and your accuracies and rank will be displayed on the Private Leaderboard. \n(Attention: you will use soft label for kaggle submission and hard label for everything else in HW1)\n</p>\n\n<h2>Data</h2>\n<p>Please ignore the empty train and test data provided in this Kaggle competition(same as the data in our HW1 data folder) and refer to the data provided in our Homework 1.</p>\n\n<h2>Submission Format</h2>\n<p>Submission file should contain two columns: patient id and predicted label. The predicted label is a soft label, which represents the possibility of mortality for each patient you predict.  Also, make sure you sign in using your GT email and corresponding username reflecting your own GT account. i.e. mliu302",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Evaluation criteria is AUC. The predicted label is a soft label, which represents the possibility of mortality for each patient you predict. The label range is between 0 and 1. 50% of the data is used for the public leaderboard where you can receive feedback on your model.The fi\fnal private leaderboard will use the remaining 50% of the data and will determine your final class ranking.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}