{
  "fetched_at": "2026-10-20T00:16:23Z",
  "source_url": "https://www.kaggle.com/competitions/cu-regression-challenge/data",
  "pages": [
    {
      "name": "rules",
      "content": "- You can submit upto 3 solutions per day.\n- Do not cheat! ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>This dataset contains house sale prices for King County, which includes Seattle. It includes homes sold between May 2014 and May 2015.</p>\n\n<p>It's a great dataset for evaluating simple regression models.\n</p>\n\n<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the test set</li>\n<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format</li>\n</ul>\n\n<h2>Data fields</h2>\n<ul>\n<li><strong>Unique_idx</strong> - Unique identifier for each row (each home can be sold multiple times; this will be unique for each sale of the same home</li>\n<li><strong>id</strong> - Unique ID for each home</li>\n<li><strong>Data</strong> - Date of home sale</li>\n<li><strong>bedrooms</strong> - Number of bedrooms</li>\n<li><strong>bathrooms</strong> - Number of bathrooms</li>\n<li><strong>sqft_living</strong> - Square footage of the apartment interior living space.</li>\n<li><strong>sqft_lot</strong> - Square footage of the land space</li>\n<li><strong>floors</strong> -Number of floors</li>\n<li><strong>waterfront</strong> -Dummy variable indicating whether apartment overlooks waterfront or not</li>\n<li><strong>view</strong> - An index 0-4 of how good the view of the property is</li>\n<li><strong>condition</strong> - An index 1-5 on the condition of the apartment</li>\n<li><strong>grade</strong> - An index 1-13; 1-3- fall short in construction and design, 7- avg level of construction and design; 11-13- high quality of construction and design</li>\n<li><strong>sqft_above</strong> - Square footage of interior housing space above ground level.</li>\n<li><strong>sqft_basement</strong> - Square footage of basement.</li>\n<li><strong>yr_build</strong> - Year the house was built.</li>\n<li><strong>yr_renovated</strong> - Year the house was renovated.</li>\n<li><strong>zipcode</strong> - Zipcode of the house</li>\n<li><strong>lat</strong> - Latitude</li>\n<li><strong>long</strong> - Longitude</li>\n<li><strong>sqft_living15</strong> - Avg square footage of the interior housing living space for nearest 15 neighbours</li>\n<li><strong>sqft_lot15</strong> - Avg square footage of the land lots for nearest 15 neighbours</li>\n<li><strong>Price</strong> - Price of each home sold</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h1> Kaggle Mini Competition 1 : Regression challenge</h1>\n<p>This is the first mini competition that you will be participating in for CSCI 4622. In this competition you will work with a dataset to predict house sale prices in King County, USA. This is a simple clean dataset in which you will use the 20 available features to predict the sale price. Training and validation data are available in the 'Data' tab. </p>\n\n\n<h2>Remember: </h2>\n<ul>\n<li> You should be working in teams of 2-3 people. You are not required to physically code together but you are encouraged to try different things and select the best model you'd like to submit.\n</li>\n<li> Competition is open from Friday (2/7/2020) at 2 PM to Wednesday (2/12/2020) at Midnight. \n</li>\n<li> Your grade on all the mini competitions account for 20% of your total grade\n</li>\n</ul>\n\n<h2> How does this work? </h2>\n<p> Your goal in this exercise is to build the best model, as a team, to predict the housing sale prices in this dataset (more information in the Data tab). How you code and work as a team is upto you: you can all work on the same code and divide work, or build different models and ensemble amongs them, or any other method you prefer. Once you build the model, you need to upload your submissions (refer to sample_submission.txt in the Data tab). You will have access to labelled training data and unlabelled validation data. Your model will be evaluated based on the root mean squared error (RMSE) obtained on this validation data. </p>\n\n<p> Based on your RMSE score, you will be assigned a rank on the Kaggle Leaderboard. This way you are able to monitor your standing in this competition.  Once the competition is closed, the person at the top of the leaderboard is the winner. But wait, there's a twist. We will hold out an additional subset of the data that your model will be evaluated on. You will be unable to see the scores on this set until the competition closes. This means rankings can change when the competition closes. Therefore, though you try to improve your rankings, remember to keep your model generalizable so that you can have the last laugh. </p>\n\n<h2> Deliverables a.k.a what you will be graded on </h2>\n\n<ul>\n<li> Your code(s)\n</li>\n<li> Short one or two page report summarizing everything you did to build your best model. It is recommended that you limit it to one page unless there is something you really want to mention that can't be fit. (You must submit a report in order to get a grade)\n</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<h2> Goal</h2>\n\n<p>It is your job to predict the sales price for each house. For each Id in the test set, you must predict the value of the SalePrice variable. </p>\n\n<h2>Metric</h2>\n\n<p>Submissions are evaluated on <a href=\"https://en.wikipedia.org/wiki/Root-mean-square_deviation\"> Root-Mean-Squared-Error </a> (RMSE) between the predicted value and the observed sales price. (Taking logs means that errors in predicting expensive houses and cheap houses will affect the result equally.)</p>\n\n<h2> Submission file format </h2>\nThe file should contain a header and have the following format:\n<pre>\nUnique_idx\tprice\n15544\t459000\n17454\t445000\n21548\t1057000\n</pre>\n\nYou can download an example submission file (sample_submission.csv) on the <a href=\"https://www.kaggle.com/c/cu-regression-challenge/data>Data page</a>.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "Competition opens on Friday (2/7/2020) and goes through Wednesday (2/12/2020). ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}