{
  "fetched_at": "2026-10-24T08:10:10Z",
  "source_url": "https://www.kaggle.com/competitions/augustparttime-1/data",
  "pages": [
    {
      "name": "rules",
      "content": "\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>\nThe training data is in airbnb_berlin_listings.csv.\n</p>\n<p>\nThe prediction data is in prediction_data.csv\n</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This mini-project will have you fitting a linear regression model to a dataset in order to predict Airbnb rental prices. After fitting a model, you will submit predictions on a subset of the original data that was removed. Whoever's predictions best fit the true prices will win!</p>\n\n<h2>The data</h2>\n\n<p>The data can be found in airbnb_berlin_listings.csv and contains data on Airbnb listings in Berlin.</p>\n\n<h2>The goal</h2>\n\n<p>Make predictions on the listing in the prediction_data.csv.</p>\n\n<h2>Deliverables</h2>\n<p>\n1) Use both gradient descent and OLS methods in building your linear regression model. <br>\n2) Submit a csv file containing the id and price of each of the listings in the prediction set.\n</p>\n<h2>Winner criteria</h2>\n\n<p>The winning model will have the lowest MSE on the prediction data.</p>\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p> Your model will be evaluated by scoring your predictions against the true prices. The evaluation function used will be MSE.\n</p>\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F2639914%2F9cefaf0e24895f6f939562151785c8af%2Fmse.jpg?generation=1576798774388344&alt=media)\n\n<p> You should submit a csv file with two columns - id and prediction. </p> \n<p> Your submission should have 99 rows of predictions. </p>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "You should submit your final prediction by Monday January 6 at 9pm EST.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prizes",
      "content": "There will be a prize but for now it is a surprise.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Kernels Requirements",
      "content": "You should have used both OLS and gradient descent. \n\nYour final predictions should be in the original scale.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}