{
  "fetched_at": "2026-10-20T08:19:43Z",
  "source_url": "https://www.kaggle.com/competitions/gigster-ml/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\r\n<ul>\r\n<li><strong>X_train.csv</strong></li>\r\n<li><strong>y_train.csv</strong></li>\r\n<li><strong>X_test.csv </strong></li>\r\n</ul>\r\n<h2>Data fields</h2>\r\n<ul>\r\n<li>running_time: Duration of movie, in minutes. Example: 157.</li>\r\n<li>number_of_screens: Number of theater screens on which it was shown. Example: 3,858.</li>\r\n<li>production_budget: Movie production budget, in USD. Example: $150,000,000</li>\r\n<li>oscar_winning_directors_present: If this empty element is in the instance, then one or more of the directors have won Oscars for previous films. In this case, the instance element also includes the element num_oscar_winning_directors, and one or more oscar_winning_director elements containing their names.</li>\r\n<li>highest_grossing_actors_present: If this empty element is in the instance, then one or more of the actors are among the 50 highest grossing actors. In this case, the instance element also includes the element num_highest_grossing_actors, and one or more highest_grossing_actor elements containing their names.</li>\r\n<li>oscar_winning_actors_present: If this empty element is in the instance, then one or more of the actors have won Oscars for previous films. In this case, the instance element also includes the element num_oscar_winning_actors, and one or more oscar_winning_actor elements containing their names.</li>\r\n<li>summer_release: Indicates whether the movie was a summer release, true or false.</li>\r\n<li>christmas_release: Indicates whether the movie was a winter holiday re- lease, true or false.</li>\r\n<li>memorial_release: Indicates whether the movie was a Memorial Day week- end release, true or false.</li>\r\n<li>independence_day: Indicates whether the movie was a July 4th holiday re- lease, true or false.</li>\r\n<li>labor_release: Indicates whether the movie was a Labor Day weekend re- lease, true or false.</li>\r\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>You will predict the opening weekend revenues of major films released in 2008 and 2009. </p>\r\n<h3>Features</h3>\r\n<p>This dataset contains a lot of features that could predict box office revenues. Some prominent candidates are: production_budget, oscar_wining_actors_present, genres, directors, christmas_release, number_of_screens.</p>\r\n<p>Many other features are for you to discover and utilize in your predictions.</p>\r\n<h3>Solution Ideas</h3>\r\n<p>You have a lot of flexibility in what you might do. You could focus on feature engineering, i.e., coming up with fancy inputs for your method, or you could focus on fancy regression techniques that use the features. Here are some ideas to get you started:</p>\r\n<ul>\r\n<li><span style=\"font-size: 1em; line-height: 1.5em;\">Basic regression on meta-data features: A good place to start is to turn the metadata into a vectorial feature representation, and use a linear regression technique like ridge regression. You could use quantitative features such as production budget, binary holiday release variables, and number of Oscar-winning actors.</span></li>\r\n<li><span style=\"font-size: 1em; line-height: 1.5em;\">Use a neural network: If you think there isn’t enough flexibility, you could go ahead and learn about multi-layer perceptrons and how to train them with backpropagation.</span></li>\r\n<li><span style=\"font-size: 1em; line-height: 1.5em;\">Use a support vector machine: If you prefer your objectives convex, you could jump the gun and learn about regression with support vector machines.</span></li>\r\n<li><span style=\"font-size: 1em; line-height: 1.5em;\">Go totally Bayesian: Worried that you’re not accounting for uncertainty? You could take a fully Bayesian approach to linear regression and marginalize out your uncer- tainty. Intrigued by the infinite-dimensional stuff I mentioned in lecture? Check out Gaussian process regression.</span></li>\r\n</ul>\r\n<h3><br />Acknowledgements</h3>\r\n<p>We thank Professor Ryan Adams and his students @ Harvard University for putting together this public dataset. </p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is <a href=\"https://en.wikipedia.org/wiki/Mean_absolute_error\">Mean Absolute Error</a>. </p>\r\n<p>Submission format:</p>\r\n<pre> box_office<br />0 20544819.3131<br />1 11785002.0506<br />2 19426880.3183<br />3 -928444.22199<br />4 -648094.084952<br />5 -1527754.84929<br />6 -1477229.93081<br />7 2972691.41906<br />8 24842724.831<br />9 -1780271.33335<br />10 -688281.496767<br />11 -2408660.41803<br />12 6396021.85459<br />13 -1180580.70351<br />etc.</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>Team mergers are not allowed in this competition.</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 50 entries per day.</p>\r\n    <p>You may select up to 50 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>3/16/2016 10:10 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>3/21/2016 11:59 PM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}