{
  "fetched_at": "2026-10-20T02:23:59Z",
  "source_url": "https://www.kaggle.com/competitions/devfest21-competition/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Information about the dataset: The dataset consists of 12,330 entries, each one representing a session (belonging to a user) in a 1-year period to avoid any tendency to a specific campaign, special day, user profile, or period. The dataset and the information about it are taken from Kaggle. However, changes may have been applied.\n\nInformation about the attributes: The dataset consists of 10 numerical and 8 categorical attributes.\n\n-Revenue: the class label.\n\n-Administrative: the number of the administrative pages visited by the user in that session.\n\n-Administrative Duration: the total time spent by the user in administrative pages\n\n-Informational: the number of the informational pages visited by the user in that session.\n\n-Informational Duration: the total time spent by the user in informational pages.\n\n-Product Related: the number of the product related pages visited by the user in that session.\n\n-Product Related Duration: the total time spent by the user in product related pages.\n\n-Bounce Rate (of a web page): the percentage of users that entered and left (bounced) the website through this same \nwebpage\n\n-Exit Rate (of a web page): the percentage of pageviews for this web page that were the last in the session\n\n-Page Value (of a web page): the average value for a web page that a user visited before completing an e-commerce \ntransaction\n\n-Special Day: the closeness of the visiting date to a special day (like Mother’s Day, Valentine's Day). The values are between 0 and 1, 0 being far from any special day and 1 being closest to a special day.\noperating system:\n\n-browser: the operating system used\n\n-region: the region of the user\n\n-traffic type: the traffic type -** visitor type:** the visitor type (new visitor or returning visitor\n\n-weekend: whether the date of the visit is weekend or not\n\n-month of the year: the month of the year of the visit",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Given various Information related to a customer’s behavior in online shopping websites,\nwe want to create a model that can predict whether that customer will generate revenue for the website's company or not.\nIt is therefore a binary classification problem\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is [Mean F1-Score](https://en.wikipedia.org/wiki/F-score). The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision ( \\text{p} ) and recall ( \\text{r} ).\nPrecision is the ratio of true positives (\\text{tp}) to all predicted positives (\\text{tp} + \\text{fp}). Recall is the ratio of true positives (\\text{tp}) to all actual positives (\\text{tp} + \\text{fn}). The F1 score is given by:\n[ \\text{F1} = 2\\frac{\\text{p} \\cdot \\text{r}}{\\text{p}+\\text{r}}\\ \\ \\mathrm{where}\\ \\ \\text{p} = \\frac{\\text{tp}}{\\text{tp}+\\text{fp}},\\ \\ \\text{r} = \\frac{\\text{tp}}{\\text{tp}+\\text{fn}} ]\nThe 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.\n\n# **Submission Format**\nFor every author in the dataset, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as its own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list A,A B C, B,B A C, C,C A B.\nThe file should contain a header and have the following format:\n`AuthorId,DuplicateAuthorIds\n1,1`",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}