{
  "fetched_at": "2026-10-20T03:04:45Z",
  "source_url": "https://www.kaggle.com/competitions/bike-sharing-demand/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p><a href=\"https://www.kaggle.com/users/993/ben-hamner/bike-sharing-demand/random-forest-benchmark\">See, fork, and run a random forest benchmark model through Kaggle Scripts</a></p>\r\n<p>You are provided hourly rental data spanning two years. For this competition, the training set is comprised of the first 19 days of each month, while the test set is the 20th to the end of the month. You must predict the total count of bikes rented during each hour covered by the test set, using only information available prior to the rental period.</p>\r\n<h2>Data Fields</h2>\r\n<p><strong>datetime</strong> - hourly date + timestamp  <br /><strong>season</strong> -  1 = spring, 2 = summer, 3 = fall, 4 = winter <br /><strong>holiday</strong> - whether the day is considered a holiday<br /><strong>workingday</strong> - whether the day is neither a weekend nor holiday<br /><strong>weather</strong> - 1: Clear, Few clouds, Partly cloudy, Partly cloudy <br />2: Mist + Cloudy, Mist + Broken clouds, Mist + Few clouds, Mist <br />3: Light Snow, Light Rain + Thunderstorm + Scattered clouds, Light Rain + Scattered clouds <br />4: Heavy Rain + Ice Pallets + Thunderstorm + Mist, Snow + Fog <br /><strong>temp</strong> - temperature in Celsius<br /><strong>atemp</strong> - \"feels like\" temperature in Celsius<br /><strong>humidity</strong> - relative humidity<br /><strong>windspeed</strong> - wind speed<br /><strong>casual</strong> - number of non-registered user rentals initiated<br /><strong>registered</strong> - number of registered user rentals initiated<br /><strong>count</strong> - number of total rentals</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p><a href=\"https://www.kaggle.com/c/bike-sharing-demand/forums/t/13228/kaggle-scripts/69563#post69563\">Get started on this competition through Kaggle Scripts</a></p>\r\n<p>Bike sharing systems are a means of renting bicycles where the process of obtaining membership, rental, and bike return is automated via a network of kiosk locations throughout a city. Using these systems, people are able rent a bike from a one location and return it to a different place on an as-needed basis. Currently, there are over 500 bike-sharing programs around the world.</p>\r\n<p>The data generated by these systems makes them attractive for researchers because the duration of travel, departure location, arrival location, and time elapsed is explicitly recorded. Bike sharing systems therefore function as a sensor network, which can be used for studying mobility in a city. In this competition, participants are asked to combine historical usage patterns with weather data in order to forecast bike rental demand in the Capital Bikeshare program in Washington, D.C.</p>\r\n<p><img src=\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3948/media/bikes.png\" alt=\"Bikes\" width=\"600\" height=\"115\" /></p>\r\n<h2>Acknowledgements</h2>\r\n<p>Kaggle is hosting this competition for the machine learning community to use for fun and practice. This dataset was provided by Hadi Fanaee Tork using data from <a href=\"http://www.capitalbikeshare.com/system-data\">Capital Bikeshare</a>. We also thank the UCI machine learning repository for <a href=\"http://archive.ics.uci.edu/ml/datasets/Bike+Sharing+Dataset\">hosting the dataset</a>. If you use the problem in publication, please cite:</p>\r\n<p>Fanaee-T, Hadi, and Gama, Joao, <em>Event labeling combining ensemble detectors and background knowledge</em>, Progress in Artificial Intelligence (2013): pp. 1-15, Springer Berlin Heidelberg.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>Submissions are evaluated one the Root Mean Squared Logarithmic Error (RMSLE). The RMSLE is calculated as</p>\r\n<p>\\[ \\sqrt{\\frac{1}{n} \\sum_{i=1}^n (\\log(p_i + 1) - \\log(a_i+1))^2 } \\]</p>\r\n<p>Where:</p>\r\n<ul>\r\n<li><span style=\"font-size: 1em; line-height: 1.5em;\">\\\\(n\\\\) is the number of hours in the test set</span></li>\r\n<li><span style=\"font-size: 1em; line-height: 1.5em;\">\\\\(p_i\\\\) is your predicted count</span></li>\r\n<li><span style=\"font-size: 1em; line-height: 1.5em;\">\\\\(a_i\\\\) is the actual count</span></li>\r\n<li><span style=\"font-size: 1em; line-height: 1.5em;\">\\\\(\\log(x)\\\\) is the natural </span>logarithm</li>\r\n</ul>\r\n<h2>Submission Format</h2>\r\n<p>Your submission file must have a header and should be structured in the following format:</p>\r\n<pre>datetime,count<br />2011-01-20 00:00:00,0<br />2011-01-20 01:00:00,0<br />2011-01-20 02:00:00,0\r\n...<br />...\r\n</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\r\n\t<!-- 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>\r\n        Privately sharing code or data outside of teams is not permitted.\r\n        It's okay to share code if made available to all participants on the forums.\r\n    </p>\r\n    <h3>Team Mergers</h3>\r\n    <p>\r\n        Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.<br/>\r\n    </p>\r\n\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 5 entries per day.</p>\r\n    <p>You may select up to 2 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>5/28/2014 9:59 PM UTC</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>5/29/2015 11:59 PM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n<ul>\r\n<li><span style=\"line-height: 1.4;\">Due to the public nature of the data, this competition does not count towards Kaggle ranking points.</span></li>\r\n<li><span style=\"line-height: 1.4;\">We ask that you respect the spirit of the competition and do not cheat. You should not submit entries based on test-set answers or train your model on the test set. Hand labeling is also forbidden.</span></li>\r\n<li><span style=\"line-height: 1.4;\">Your model should only use information which was available prior to the time for which it is forecasting.</span></li>\r\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}