{
  "fetched_at": "2026-10-19T21:22:56Z",
  "source_url": "https://www.kaggle.com/competitions/apple-app/data",
  "pages": [
    {
      "name": "rules",
      "content": "<h3>Team Limits</h3>\n<p>Each team is limited to have no more than <strong>3</strong> persons.</p>\n<h3>Submission Limits</h3>\n<p>You may submit a maximum of <strong>5</strong> entries per day.</p>\n<p>You may select up to <strong>3</strong> final submissions for judging.</p>\n<h3>Competition Timeline</h3>\n<p>Start Date: <strong>April 17, 2019</strong></p>\n<p>End Date: <strong>June 1, 2019, 11:59PM</strong></p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<p>With million of apps around nowadays, mobile app analytics is a great way to understand the existing strategy to drive growth and retention of future user. This data set contains more than 7000 Apple iOS mobile application details, e.g. size, price, genre, rating_count, description and etc. The data was extracted from the iTunes Search API at the Apple Inc website. The goal is to predict whether the overall rating for the app is more than 4 stars (1=yes, 0=no), which we think it a very good app.</p>\n<h2>File descriptions</h2>\n<ul>\n<li><strong>app_train.csv</strong> - the training set</li>\n<li><strong>app_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<h2>Data fields</h2>\n<p>There are 16 variables:</p>\n<ul>\n<li><strong>id</strong> - App ID</li>\n<li><strong>track_name</strong> - App Name</li>\n<li><strong>size_bytes</strong> - Size (in Bytes)</li>\n<li><strong>currency</strong> - Currency Type</li>\n<li><strong>price</strong> - Price amount</li>\n<li><strong>rating_count_tot</strong> - User Rating counts (for all version)</li>\n<li><strong>rating_count_ver</strong> - User Rating counts (for current version)</li>\n<li><strong>ver</strong> - Latest version code</li>\n<li><strong>cont_rating</strong> - Content Rating</li>\n<li><strong>prime_genre</strong> - Primary Genre</li>\n<li><strong>sup_devices.num</strong> - Number of supporting devices</li>\n<li><strong>ipadSc_urls.num</strong> - Number of screenshots showed for display</li>\n<li><strong>lang.num</strong> - Number of supported languages</li>\n<li><strong>vpp_lic</strong> - Vpp Device Based Licensing Enabled</li>\n<li><strong>desc</strong> -  Application description</li>\n<li><strong>rating</strong> -  Whether the overall user rating is above 4 stars or not (1=yes, 0=no)</li>\n</ul>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>This competition is an in-class competition for the course \"Artificial Intelligence and Machine Learning (Spring 2019)\" in Renmin University of China.</p>\n<p>The competition is to predict the overall rating for an Apple iOS App, whether above four stars (when we think the App is successful) or not. </p>\n<h2>Acknowledgements</h2>\n<p>We thank Ramanathan Perumal for providing this dataset. The data was extracted from the iTunes Search API at the Apple Inc website around July 2017.</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://www.kaggle.com/wiki/MeanFScore\"> Mean F1-Score</a>. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:</p>\n<p>\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]</p>\n<p>The F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.</p>\n<h2>Submission Format</h2>\n<p>For <strong>every app</strong> in the dataset, submission files should contain two columns: id and rating, i.e. the App ID and the predicted rating for the App whether it is above four stars (rating=1) or not (rating=0).</p>\n<p>The file should contain a header and have the following format:</p>\n<pre>id,rating<br>1071712425,1<br>346184215,0<br>893525571,0<br>......</pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}