{
  "fetched_at": "2026-10-19T23:33:28Z",
  "source_url": "https://www.kaggle.com/competitions/PhotoQualityPrediction/data",
  "pages": [
    {
      "name": "Description",
      "content": "<p><strong>Background</strong></p>\r\n<p>We have a large collection of user-generated photos. We want to automatically pick out particularly enjoyable or impressive ones to highlight, especially travel-related, using only the meta-data associated with the images such as caption text, image dimensions\r\n and approximate location in the world. We know from our preliminary experiments and intuition that certain words and places are correlated with good photos, and others are indicators of less enjoyable pictures, but we would like to develop an algorithm to\r\n tie together these multiple signals.</p>\r\n<p><strong>Objective</strong></p>\r\n<p>Given anonymized information on thousands of photo albums, predict whether a human evaluator would mark them as 'good'.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p><strong>Data format</strong></p>\r\n<p>For anonymity reasons, the caption, title and description texts have been broken down into word tokens, and the most common (excluding stop words) have been encoded as numbers. The fields are:</p>\r\n<ul>\r\n<li><em>latitude</em>: The integrally-rounded latitude of the location of the album\r\n</li><li><em>longitude</em>: The integrally-rounded longitude of the location of the album\r\n</li><li><em>width</em>: The width of the images in the album, in pixels </li><li><em>height</em>: The height of the images in the album, in pixels </li><li><em>size</em>: The number of photos in the album </li><li><em>name</em>: The common tokens in the name of the album </li><li><em>description</em>: The common tokens in the description of the album </li><li><em>caption</em>: The common tokens in all the captions of the photos within the album\r\n</li><li><em>good</em>: 1 means the human reviewer liked the album, 0 means they didn't. This is the variable we want to predict.\r\n</li></ul>\r\n<p><strong>Notes</strong></p>\r\n<p>From our own experiments, we know there's obvious correlations that make sense, such as areas in Africa rich in wildlife having a high proportion of good photos, and certain words that are associated with poor albums. Our goal is to turn some of those informal\r\n correlations into a more rigorous model we can reuse on much larger data sets.</p>\r\n<p>To encode the text I'm creating a whitelist of words, consisting of non-stop-words that occur more than twenty times in different albums. For each word in that list, I assign a numerical value, and write out the numbers of all the words that appear in each\r\n album's title, description and photo captions.</p>\r\n<p>The main goal of this exercise is to ensure that there's not enough information to reconstruct the text, whilst still having enough content for a prediction algorithm to sink its teeth into. I've done some preliminary work to make sure there are promising\r\n signals in the data that's remaining, and there do seem to be strong correlations, so I'm hopeful it's a good compromise.</p>\r\n<p>Why don't we make the image data available? Our application needs to make quality decisions on very large volumes of externally-hosted images in a short amount of time, so image processing solutions aren't feasible for us. We're hopeful that the meta-data\r\n will provide a good enough approximation to be useful</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Prizes",
      "content": "<p><strong>1st place =&nbsp;</strong>$2,500</p>\r\n<p><strong>2nd place =&nbsp;</strong>$1,500</p>\r\n<p><strong>3rd place</strong>&nbsp;= $1,000</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>This competition uses a capped binomial deviance method as described <a href=\"https://www.kaggle.com/c/ChessRatings2/Details/Evaluation\">\r\non the Chess Ratings 2 competition page</a>&nbsp;and <a href=\"http://www.kaggle.com/c/ChessRatings2/forums/t/285/binomial-deviance\">\r\nin the forums</a>.</p>",
      "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 2 entries per day.</p>\r\n    <p>You may select up to 5 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>10/29/2011 6:57 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>11/20/2011 11:59 PM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}