{
  "fetched_at": "2026-10-19T07:41:29Z",
  "source_url": "https://www.kaggle.com/competitions/endava-customer-retention-hackathon/data",
  "pages": [
    {
      "name": "data-description",
      "content": "This page appears alongside the data files. It describes what files have been provided and the format of each. There is no single format for this page that is appropriate for all competitions, but you should strive to describe as much as you can here. A little time spent describing the data here can save a lot of time answering questions later.\n\n## Files\n\n*   **train_data.csv** - the training set\n*   **members.csv** - dataset with information about members\n*   **transactions.csv** - dataset with information about transactions\n*   **user_logs.csv** - dataset with logs about user behaviour \n*   **kaggle_test_data.csv** - the test set\n\n\n**train_data.csv** - the train set, containing the user ids and whether they have churned.\n- msno: user id\n- is_churn: This is the target variable. Churn is defined as whether the user did not continue the subscription within 30 days of expiration. is_churn = 1 means churn,is_churn = 0 means renewal.\n\n**members.csv** - user information. Note that not every user in the dataset is available.\n- msno\n- city\n- bd: age. Note: this column has outlier values ranging from -7000 to 2015, please use your judgement.\n- gender\n- registered_via: registration method\n- registration_init_time: format %Y%m%d\n\n**transactions.csv** - transactions data until 3/31/2017.\n- msno: user id\n- payment_method_id: payment method\n- payment_plan_days: length of membership plan in days\n- plan_list_price: in New Taiwan Dollar (NTD)\n- actual_amount_paid: in New Taiwan Dollar (NTD)\n- is_auto_renew\n- transaction_date: format %Y%m%d\n- membership_expire_date: format %Y%m%d\n- is_cancel: whether or not the user canceled the membership in this transaction.\n\n**user_logs.csv** - daily user logs describing listening behaviors of a user. Data collected until 3/31/2017.\n- msno: user id\n- date: format %Y%m%d\n- num_25: # of songs played less than 25% of the song length\n- num_50: # of songs played between 25% to 50% of the song length\n- num_75: # of songs played between 50% to 75% of of the song length\n- num_985: # of songs played between 75% to 98.5% of the song length\n- num_100: # of songs played over 98.5% of the song length\n- num_unq: # of unique songs played\n- total_secs: total seconds played\n\n **kaggle_test_data.csv** - the test set with msno for generating predictions\n- msno: user id\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on [area under the ROC curve](http://en.wikipedia.org/wiki/Receiver_operating_characteristic) between the predicted probability and the observed target.\n\n\n## Submission File\nFor each ID in the test set, you must predict a probability for the TARGET variable. The file should contain a header and have the following format:\n\nmsno,is_churn\n    9WQJvVyggkLWsp0DLpOljfbKePSZZZeYdQvNOAkQ0bk=,0\n    kTCflEFCJk6ahA8ryiGzOBQlhwEOMxuPT7gVPRzoJJ8=,1\n    EgBTyrvGcPR2bjlXjPqdSkRzz1NVXVvLLdUaabKBm4I=,0\n    etc.\n\nSubmission has to have 24274 rows plus a header (24275 rows in total). msno needs to match the test.csv msno.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Teams must be composed of at least 2 members.  \n- In case you don't have a team, please register as an individual. We'll do our best to find you a match. \n- Make the results should be uploaded to Kaggle by one team member.\n- Event day: please bring your own hardware (laptops, chargers, etc.). Temporary Google Cloud accounts will be provided.  \n - Have fun! :) ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "In this Churn Hack/Data-thon, powered by Kaggle, you'll learn and compete using the latest machine learning and data warehousing tools on Google Cloud. Rich dataset from the Media industry will allow you to derive insights that would be of most use to your business. Unleash your creativity and explore the possibilities with some examples given below: \n  \n·         Analyzing customer churn and its reasons \n·         Generating personalized products and loyalty offerings using predictive analytics \n·         Insights and trend predictions \n\n**Goal:**\nWhen you write this section, try to summarize your competition’s goal. It will help your participants quickly understand their objective.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}