{
  "fetched_at": "2026-10-20T09:58:04Z",
  "source_url": "https://www.kaggle.com/competitions/datahack/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p><strong>File descriptions</strong></p>\r\n<p><strong>train_dataset.csv</strong> - the training data. The training dataset comprises 300 data-points with 16 dimensional inputs and one dimensional real-valued outputs.</p>\r\n<p><br /><strong>test_dataset.csv</strong> - the test set inputs. The test dataset comprises 200 data-points with 16 dimensional input features. The outputs are missing and the goal is to predict them. In addition, at some of the test points a subset of the inputs is also missing. The test inputs are also available as a CSV file in the same format as the training data. Missing inputs and indicated by the value NA.</p>\r\n<p><br /><strong>sample_submission.csv</strong> - a sample submission file in the correct format. For each test datapoint you must predict the missing real-valued output. These predictions should be submitted in the same format as the training outputs. The first row must contain column names (ID, Total.Interactions). Below this row, the first column must contain the data-point index (that runs from 1 through to 200) and the second column must contain the predictions (integer numbers).</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>Here are the key details for the regression competition:</p>\r\n<p><strong>Description of training data</strong></p>\r\n<p>The training dataset comprises 300 data-points with 16 dimensional inputs and one dimensional real-valued outputs. The training dataset is available as a CSV file. The first row of each CSV file contains the column names and the first column contains the data-point index (running from 1 to 300). There are standard functions to read these files in many programming languages, e.g. read.csv in R and csv.reader or numpy.loadtxt in Python.</p>\r\n<p><strong>Description of test data</strong></p>\r\n<p>The test dataset comprises 200 data-points with 16 dimensional input features. The outputs are missing and the goal is to predict them. In addition, at some of the test points a subset of the inputs is also missing. The test inputs are also available as a CSV file in the same format as the training data. Missing inputs are indicated by the value NA.</p>\r\n<p><strong>Submission of predictions</strong></p>\r\n<p>For each test datapoint you must predict the missing real-valued output. These predictions should be submitted in the same format as the training outputs. The first row must contain column names (ID, Total.Interactions). Below this row, the first column must contain the data-point index (that runs from 1 through to 200) and the second column must contain the predictions (integer numbers).</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p><strong>Evaluation metric</strong></p>\r\n<p>The Root Mean Squared Error (RMSE) will be used for evaluation. The RMSE is defined as the root of the average squared error between the prediction and groundtruth.</p>\r\n<p><img src=\"https://s4.postimg.org/ibb1pbbst/rmse.png\" alt=\"rmse\" width=\"359\" height=\"132\" style=\"display: block; margin-left: auto; margin-right: auto;\" /></p>\r\n<p>Outputs associated with missing inputs contribute equally to those without.</p>\r\n<p><strong>Leaderboard and final evaluation</strong></p>\r\n<p>The predictions on 50% of the test data points are used to score the submission according to the RMSE and maintain a public leaderboard. The predictions on the remaining 50% of the test data points will be used, after the competition closes, for the final evaluation. This prevents overfitting on the public test data.</p>\r\n<p><strong>Submission rules</strong></p>\r\n<p>Each team may only submit 10 sets of predictions each day. When the competition closes, each team will select 1 set of predictions to put forward for the final evaluation.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "<!-- Begin Base Rules -->\r\n<h3>One account per participant</h3>\r\n<p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n<h3>No private sharing outside teams</h3>\r\n<p>Privately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.</p>\r\n<h3>Team Mergers</h3>\r\n<p>Team mergers are not allowed in this competition.</p>\r\n<h3>Team Limits</h3>\r\n<p>There is no maximum team size.</p>\r\n<h3>Submission Limits</h3>\r\n<p>You may submit a maximum of 10 entries per day.</p>\r\n<p>You may select only 1 final submissions for judging.</p>\r\n<h3>Competition Timeline</h3>\r\n<p>Start Date: <strong>6/3/2017 12:00 AM IST</strong></p>\r\n<p>Merger Deadline: <strong>None</strong></p>\r\n<p>Entry Deadline: <strong>None</strong></p>\r\n<p>End Date: <strong>8/3/2014 11:59 PM IST</strong></p>\r\n<!-- End Base Rules -->\r\n<p>The rules page is a bit special: it will auto-update the text based on the parameters of the competition. The rules you need to add here are any additional rules relating to dataset usage. You may also put grading information here.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}