{
  "fetched_at": "2026-10-19T16:54:48Z",
  "source_url": "https://www.kaggle.com/competitions/data-mining-assignment1/data",
  "pages": [
    {
      "name": "data-description",
      "content": "A food store in Pakistan has provided data set for this project dated between September 17, 2014, and October 26, 2014 (6 weeks approx.). The dataset involves only three columns. Total rows are 1058198 and each row represents the purchasing done by customers in each day.\n\n## Files\n\n*   **Retail_customer.csv** - the training set\n*   **Submission.csv** - the test set\n*   **Sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\n\n*   `Customer_ID` - Defines a customer who buys from store\n*   `Sales Amount ` - Represents sales on each day\n*   `Sales Date`-Represents the day in which sales are done",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Task",
      "content": "You have to compare your rule based derived label (Churned/Not Churned) with the actual label (provided) to find the difference/error. Exclude those customers which are in testing label file. Show the difference in percentage.\n\nTask 1:\n\n Preprocess the dataset and make a feature set (provided above).\n\n Label the customer as churn/Not-churn?\n\n Make a model for churn prediction, i.e., provided customers in test data will churn or not?\n\nA customer will churn if he/she has no visit in a week.\n\nEDA:\n\n Calculate the week with the highest earning?\n\n Identify the most valued customer?\n\n Categorize the customers into 3 groups (i.e., Poor, Mediocre, Rich)\n\n Will we able to figure out churn important factors from available data?\n\n How Churn Rate changes with Historical Visits? Answer this query with the help of graph?\n\nYou have to submit the predicted outputs for customers provided in Submission.csv on Kaggle.",
      "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
    },
    {
      "name": "abstract",
      "content": "In today's retail world, competition is fierce as stores strive to understand their top customers and find ways to keep them coming back. With an explosion of data available, savvy retailers are realizing its potential for profit. They're putting more effort into using this data effectively, integrating it into their decision-making processes to gain an edge and boost profits.\n\nIn this Competition, you have to address the issue of churn prediction and customer retention in the retail industry. This would not only help retailers plan retention strategies for their most profitable customers but also design effective marketing programs for the future. In this way, companies can retain their valued customers and make cost-effective marketing strategies solely targeted to the right customer base.\n\nConsumer churn occurs when a buyer discontinues his or her dealings with an organization. In retail, a buyer is considered churned once his/her last transaction exceeds a certain amount of time. Once a profitable consumer becomes a churn, the organization experiences a loss not just in lost profits but also in the cost of making new marketing plans and strategies to attract a new customer base.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}