{
  "fetched_at": "2026-10-20T08:56:23Z",
  "source_url": "https://www.kaggle.com/competitions/credit-risk-classifier-xm/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The modified dataset contains 1400 entries with 20 categorial/symbolic attributes. In this dataset, each entry represents a person who takes credit by a bank. Each person is classified as good or bad credit risks according to the set of attributes. The link to the original dataset (1000 entries) can be found below.\n\nReference to the original data source: [https://archive.ics.uci.edu/ml/datasets/statlog+(german+credit+data)](url)\n\nYou can find a sample visualization from here: [https://www.kaggle.com/kabure/predicting-credit-risk-model-pipeline](url)\n\nThe dataset has been split into a 80/20 training/test split. The files are csv. Please perform data analysis on the training file to predict the classification as good or bad credit risks. \n\nTry to get an accuracy score above .68.\n\n**Age** (numeric)\n**Sex** (text: male, female)\n**Job** (numeric: 0 - unskilled and non-resident, 1 - unskilled and resident, 2 - skilled, 3 - highly skilled)\n**Housing** (text: own, rent, or free)\n**Saving accounts** (text - little, moderate, quite rich, rich)\n**Checking account** (numeric, in DM - Deutsch Mark)\n**Credit amount** (numeric, in DM)\n**Duration** (numeric, in month)\n**Purpose**(text: car, furniture/equipment, radio/TV, domestic appliances, repairs, education, business, vacation/others\n**Risk** (Value target - Good or Bad Risk)\n\n## Files\n\n*   **credit_training_data.csv** - the training data set \n*   **credit_test_data.csv** - the test data set \n*   **sample_submission.csv** - a sample submission file in the correct format \n\n## Columns\n\n*   `example_id` - definition of example_id\n*   `feature_1` - definition of feature_1\n*   etc.\n*   `Age` (numeric)\n*   `Sex` (text: male, female)\n*   `Job` (numeric: 0 - unskilled and non-resident, 1 - unskilled and resident, 2 - skilled, 3 - highly skilled)\n*   `Housing` (text: own, rent, or free)\n*   `Saving accounts` (text - little, moderate, quite rich, rich)\n*   `Checking account` (numeric, in DM - Deutsch Mark)\n*   `Credit amount` (numeric, in DM)\n*   `Duration` (numeric, in month)\n*   `Purpose` (text: car, furniture/equipment, radio/TV, domestic appliances, repairs, education, business, vacation/others\n*   `Risk` (Value target - Good or Bad Risk)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "You may use these classifiers -\n*   Naive Bayes Algorithm\n*   Decision Tree Algorithm\n*    KNN\n*    LogisticRegression\n\nIn order to evaluate these classifiers, please show\n*    Accuracy score\n\nYou may also practice by using\n*    Cross-Validation Score\n*    Confusion Matrix\n*    Precision Score\n*    Recall Score\n*    F1 Score\n\nTry to improve your model's accuracy by performing Feature Engineering and Tuning your parameters.\nTry to add each of the categorical features to the model, by One-hot encoding.\nTry removing some of your numerical feature that has a low correlation coefficient.\n\nTry to get: an accuracy score of at least 0.68",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submit the file on Kaggle.\n\n\n## Submission File\nFor each row in the test set, you must predict a credit classification of 'good' or 'bad'. The file should contain a header and have the following format:\n\n  ID       Risk\n  1             bad\n  2           good\n  3            bad\n  4           good\n       etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Try to get an accuracy score of at least 0.68.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "The original dataset contains 1000 entries with 20 categorial/symbolic attributes prepared by Prof. Hofmann. In this dataset, each entry represents a person who takes credit by a bank. Each person is classified as good or bad credit risks according to the set of attributes. \n\nThe original dataset had data imbalance for 'good' and 'bad' credit, there were 700 'good' credits and only '300' bad credits. I have modified the dataset to be more balanced by increasing the number of 'bad' credits. The resampling technique was done by oversampling the minority class with random replications.\n\nPerform classification on the updated credit risk dataset to decide whether a particular person would be deemed to have a 'good' or 'bad' credit rating.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}