# Kaggle Community Olympiad-AI Durg Credit Card Attr — Data

来源：https://www.kaggle.com/competitions/ai-durg-credit-card-churn/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The dataset simulates anonymized customer-level credit card data and is split into training and testing files.

### `train.csv`

This file contains the features for each customer, along with the churn label (`Attrition_Flag`).

**Columns include:**

* `CLIENTNUM`: Unique customer identifier
* `Customer_Age`: Age of the customer
* `Gender`: Gender of the customer
* `Dependent_count`: Number of dependents
* `Months_on_book`: How long the account has been active
* `Total_Relationship_Count`: Number of products customer is engaged with
* `Total_Revolving_Bal`: Customer’s revolving balance
* `Avg_Utilization_Ratio`: Average card utilization ratio
* `Attrition_Flag/loan_defaulted` : Target variable — 1 if the customer churned, 0 otherwise

**Sample:**

```csv
CLIENTNUM,Customer_Age,Gender,Dependent_count,loan_defaulted
768805383,45,M,3,0
818770008,49,F,5,0
```

---

### `test.csv`

Contains the same features as `train.csv`, but without the target column. Your job is to predict the `loan_defaulted`.

**Note:** Keep the same column order as in the training data.

---

### `sample_submission.csv`

Use this format for submitting your predictions. Each row must include:

* `CLIENTNUM`: From the test set
* `loan_defaulted`: Your predicted label (0 = not churned, 1 = churned)

**Sample:**

```csv
id,loan_defaulted
768805383,0
818770008,1
```

---