{
  "fetched_at": "2026-10-19T22:50:31Z",
  "source_url": "https://www.kaggle.com/competitions/cse517a-fl23-application-project-milestone-3/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "For this Kaggle competition portion of Milestone 3, you are given a test dataset on which you'll be tested. You are free to use whatever tools you have, including but not limited to, the things you learned in class, the insights you gathered from previous Milestones, and outside resources on implementing effective ML!\n\nHere is a handy link to Kaggle's [competition documentation](https://www.kaggle.com/docs/competitions), which includes, among other things, instructions on [submitting predictions](https://www.kaggle.com/docs/competitions#making-a-submission).\n\n\n## Competition\nMore information on the competition evaluation is described in the Evaluation tab on the left.\n\n# Report\nFor Milestone 3, there is no set of instructions you have to follow. However, your report must describe the following:\n\n1. Which feature engineering and preprocessing steps you took and why.\n2. Which model/machine learning algorithm you chose and why.\n3. How you optimized the hyperparameters of your machine learning algorithm.\n\nYou may include any further information that you would like to explain. Furthermore, in your code (notebook/kernel), you must provide brief documentation so that we can refer to your report to know more about your choices. This documentation doesn't have to be extensive, we just want to see which ideas you implemented, how you implemented them, and why through the code and the notebook.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Your performance will be evaluated according to your predictions on the test data. We will provide the entire test dataset but with the target column omitted. You must train your machine learning model on the training set you have been working on to predict the targets on the test data and submit your predictions.\n\n## Grading\nAs mentioned on [Canvas](https://wustl.instructure.com/courses/97407/assignments/440384?module_item_id=1438094), Milestone 3 is worth 20 points, consisting of:\n\n- 8 points for code/kernel and report\n- 6 points for beating baseline 1\n- 6 points for beating baseline 2\n- 2 (bonus) points for first, second, and third place submissions\n\nThe 8 points for code/kernel and report rely mostly on your written report, but a small part of it is the documentation you provide in your code.\n\n## Metric\n\nThe evaluation metric for this competition is [RMSE](https://en.wikipedia.org/wiki/Root-mean-square_deviation). The RMSE, commonly used for regression tasks, is the square root of the mean-squared error.\n\n## Baselines\n\nBaseline 1: 0.2000\nBaseline 2: 0.1700\n\n## Public vs. Private scores\n\nWhen you submit your predictions, you'll have a public score based on a subset of the test data (50%) and a private score based on the rest. You'll be able to see your public score as soon as you submit a prediction, but the private score will only be revealed after the deadline. The private score will determine your final performance in this competition.\n\n## Submission format\n\nSubmission files should contain two columns: \"Id\" and \"target\", and the file should contain a header and have the following format:\n```\nId,target\n1,0.1\n```\nNote that due to Kaggle's own limitations, you are limited to 20 submissions each day (UTC). You may choose which submission to be evaluated. Otherwise, the system will simply choose the best one.\n\n## Code/Notebook\n\nTo verify your work, you must create a notebook on Kaggle that generated your submission, or link your github in the report. If you're using Kaggle to submit your code, be sure to share it with the following username for grading: cynthiazma",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": " - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "This is the home page of the competition. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}