{
  "fetched_at": "2026-10-20T07:38:39Z",
  "source_url": "https://www.kaggle.com/competitions/dsntelecomschurn2018/data",
  "pages": [
    {
      "name": "rules",
      "content": "\t<!-- Rules -->\n    <h3>One account per participant</h3>\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\n  \n    <h3>Team Mergers</h3>\n    <p>Team mergers are not allowed in this competition.</p>\n\n    <h3>Team Limits</h3>\n    <p>No team. It is an individual project..</p>\n    <h3>Submission Limits</h3>\n    <p>You may submit a maximum of 5 entries per day.</p>\n    <p>You may select up to 2 final submissions for judging.</p>\n\n    <h3>Competition Timeline</h3>\n    <p>End Date: <strong>20/02/2018 12:00 AM UTC</strong></p>\n\t<!-- End Base Rules -->\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>File descriptions</h2>\n<ul>\n<li><strong>train.csv</strong> - the training set</li>\n<li><strong>test.csv</strong> - the test set</li>\n<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>\n\n</ul>\n<h2>Data fields</h2>\n<ul>\n•\tTotal Spend in Months 1 and 2 of 2017: The total spend of a customer  in the months July & August 2017.\n\n•\tTotal SMS Spend: The total spend on SMS by a customer revenue earned through the SMS service used by the subscriber.\n\n•\tTotal Data Spend: The total amount spend on Data/Internet by a customer revenue earned through the SMS service used by the subscriber.\n\n•\tTotal Data Consumption : The total data consumed by a subscriber in KB over the period under study\n\n•\tTotal Unique Calls: The total count of unique calls made by a subscriber during the period under review\n\n•\tTotal Onnet spend: The total spend of a customer to make on-network calls (on the same network as the subscriber)\n\n•\tTotal Offnet spend:  Aggregate of Off Net Revenue: The total spend of a customer to make  off-network calls (not the same network as the subscriber) \n\n•\tCustomer Tenure in Months: The time passed since the subscriber started using the services of the network provider and counted in months\n\n•\tNetwork type subscription in Month 1: This indicates preferred network subscription of a customer, which may indicate their type of device - 2G or 3G service.\n\n•\tNetwork type subscription in Month 2: This indicates preferred network subscription of a customer, which may indicate their type of device - 2G or 3G service in the month after.\n\n•\tTotal Call centre complaint calls: The number of complaints made by the subscribers.\n\n•\tMost Loved Competitor network in in Month 1: This information certainly have a huge impact on as it gives the information about which other service provider prefer and may likely move to \n\n•\tMost Loved Competitor network in in Month 2: This information certainly have a huge impact on as it gives the information about which other service provider prefer and may likely move to\n\n•\tChurn Status: This is an indicator of a customer who leaves the network or not. 1 means the customer has churned and 0 means no churn. \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Churn happens when customers are leaving their current service provider and moving to another one. This is a big business problem because it is more expensive to acquire a new customer than to keep an existing one from leaving. This explains this challenge, which is one of the pre-qualification to the 2018 Data Science Nigeria all-expense paid bootcam/hackathon scheduled to hold 10-15 October, 2018.\n\nRead up, fine your model, build incremental statistical thinking and reinforce your Data Science career growth.\n\nAn academic data has been used here to help participants classify potential customers who might churn. Please note that a balanced dataset has been used\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The submission quality metric is accuracy. \n\nAccuracy is calculated as the ratio of correct predictions to the number of total observations. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}