{
  "fetched_at": "2026-10-24T10:35:54Z",
  "source_url": "https://www.kaggle.com/competitions/customer-churn-prediction-competition/data",
  "pages": [
    {
      "name": "data-description",
      "content": "RowNumber—corresponds to the record (row) number and has no effect on the output.\nCustomerId—contains random values and has no effect on customer leaving the bank.\nSurname—the surname of a customer has no impact on their decision to leave the bank.\nCreditScore—can have an effect on customer churn, since a customer with a higher credit score is less likely to leave the bank.\nGeography—a customer’s location can affect their decision to leave the bank.\nGender—it’s interesting to explore whether gender plays a role in a customer leaving the bank.\nAge—this is certainly relevant, since older customers are less likely to leave their bank than younger ones.\nTenure—refers to the number of years that the customer has been a client of the bank. Normally, older clients are more loyal and less likely to leave a bank.\nBalance—also a very good indicator of customer churn, as people with a higher balance in their accounts are less likely to leave the bank compared to those with lower balances.\nNumOfProducts—refers to the number of products that a customer has purchased through the bank.\nHasCrCard—denotes whether or not a customer has a credit card. This column is also relevant, since people with a credit card are less likely to leave the bank.\nIsActiveMember—active customers are less likely to leave the bank.\nEstimatedSalary—as with balance, people with lower salaries are more likely to leave the bank compared to those with higher salaries.\nExited—whether or not the customer left the bank.\nComplain—customer has complaint or not.\nSatisfaction Score—Score provided by the customer for their complaint resolution.\nCard Type—type of card hold by the customer.\nPoints Earned—the points earned by the customer for using credit card.\n\nAcknowledgements\n\nAs we know, it is much more expensive to sign in a new client than keeping an existing one.\n\nIt is advantageous for banks to know what leads a client towards the decision to leave the company.\n\nChurn prevention allows companies to develop loyalty programs and retention campaigns to keep as many customers as possible.\n\n## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Customer churn prediction is a vital analytical process for businesses looking to reduce customer attrition and retain their existing customer base. Churn, or customer attrition, occurs when customers stop doing business with a company, which can be costly and detrimental to long-term profitability. To address this issue, many businesses employ customer churn prediction models to identify customers at risk of churning and take proactive measures to retain them. Here's an overview of customer churn prediction:\n\n1. **Data Collection**: The first step in customer churn prediction is gathering data. This data often includes customer demographics, transaction history, usage patterns, customer interactions, and more. This data is collected from various sources, such as CRM systems, databases, and customer feedback.\n\n2. **Data Preprocessing**: Once the data is collected, it needs to be cleaned and prepared for analysis. This involves handling missing data, dealing with outliers, and transforming data into a suitable format for modeling.\n\n3. **Feature Engineering**: Feature engineering involves selecting and creating relevant features from the data that can be used in the churn prediction model. These features might include customer tenure, purchase frequency, customer support interactions, and any other relevant information.\n\n4. **Model Selection**: There are various machine learning and statistical models that can be used for customer churn prediction, including logistic regression, decision trees, random forests, neural networks, and more. The choice of the model depends on the complexity of the problem and the available data.\n\n5. **Training the Model**: The selected model is trained on historical data, using a portion of the dataset to learn the patterns and relationships that indicate potential churn. The remaining data is used for testing and evaluating the model's performance.\n\n6. **Evaluation:** Model performance is assessed using various metrics such as accuracy, precision, recall, F1-score, and ROC AUC. The model should be evaluated on its ability to correctly predict churn and minimize false positives.\n\n7. **Deployment**: Once a satisfactory model is developed, it can be deployed into a business's operational systems. Real-time data can be fed into the model to make predictions on current customers' churn likelihood.\n\n8. **Actionable Insights**: Churn prediction models should not only identify at-risk customers but also provide actionable insights for retaining them. This might involve offering targeted promotions, personalized communication, or improving customer service.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on accuracy score 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 \n\n```python\nCustomer_Id ,Churn\n19073,    0\n61023,    0\n42451,    1\n61656,    0\netc. \n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n - Don't cheat!\n - Try it yourself\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Customer churn prediction is a vital analytical process for businesses looking to reduce customer attrition and retain their existing customer base. Churn, or customer attrition, occurs when customers stop doing business with a company, which can be costly and detrimental to long-term profitability. To address this issue, many businesses employ customer churn prediction models to identify customers at risk of churning and take proactive measures to retain them.\n\nThe main objective of this competition is to predict the churn.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}