Dark Mode
Credit Card User Behaviour Dataset
Not Specified
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset is designed to help bank managers predict which credit card customers are likely to stop using their services, often referred to as churning. The primary goal is to empower banks to proactively engage with these customers by offering improved services, thereby influencing their decision to stay. The dataset contains details for approximately 10,100 credit card customers, covering a range of demographic, financial, and product-related attributes. A key challenge highlighted is the imbalance in the data, with only around 16% of customers having churned, which can make predictive model training more difficult.
Columns
- CLIENTNUM: A unique identifier for each customer holding an account.
- Attrition_Flag: An internal event variable indicating whether the account is closed (1) or still active (0).
- Customer_Age: The customer's age in years.
- Gender: The customer's gender, represented as M for Male and F for Female.
- Dependent_count: The number of dependents associated with the customer.
- Education_Level: The educational qualification of the account holder, such as high school or college graduate.
- Marital_Status: The marital status of the customer, including Married, Single, Divorced, or Unknown.
- Income_Category: The annual income category of the account holder, ranging from '< $40K' to '> $120K', including 'Unknown'.
- Card_Category: The type of credit card held by the customer (e.g., Blue, Silver, Gold, Platinum).
- Months_on_book: Represents the duration of the customer's relationship with the bank in months.
- Total_Relationship_Count: The total number of products held by the customer with the bank.
- Months_Inactive_12_mon: The number of months the account was inactive within the last 12 months.
- Contacts_Count_12_mon: The number of contacts made with the customer in the last 12 months.
- Credit_Limit: The credit limit assigned to the credit card.
- Total_Revolving_Bal: The total revolving balance on the credit card.
- Avg_Open_To_Buy: The average open-to-buy credit line over the last 12 months.
- Total_Amt_Chng_Q4_Q1: The change in transaction amount from the fourth quarter to the first quarter.
- Total_Trans_Amt: The total transaction amount over the last 12 months.
- Total_Trans_Ct: The total transaction count over the last 12 months.
- Total_Ct_Chng_Q4_Q1: The change in transaction count from the fourth quarter to the first quarter.
- Avg_Utilization_Ratio: The average credit card utilisation ratio.
- Naive_Bayes_Classifier_Attrition_Flag_Card_Category_Contacts_Count_12_mon_1: A score from a Naive Bayes Classifier.
- Naive_Bayes_Classifier_Attrition_Flag_Card_Category_Contacts_Count_12_mon_2: A second score from a Naive Bayes Classifier.
Distribution
The dataset is provided in CSV format (BankChurners.csv) and has a file size of 1.51 MB. It comprises approximately 10,100 customer records, each with 23 columns of data. The dataset exhibits no missing or mismatched values. An important characteristic is that 84% of customers are existing customers, while only 16% are attrited customers, making it an imbalanced dataset for predictive modelling.
Usage
This dataset is ideally suited for:
- Developing machine learning models to predict customer churn.
- Aiding bank managers in identifying and understanding customers at risk of leaving.
- Informing proactive customer retention strategies and service improvements.
- Conducting customer behaviour analysis within the banking sector.
Coverage
The dataset focuses on credit card customers and includes demographic information such as age, gender, education level, marital status, and income category. It captures customer activity and financial metrics primarily over the last 12 months, with some metrics reflecting changes between quarters. Geographic coverage is not specified within the provided details. The data reflects a specific snapshot in time, with an expected update frequency of "Never".
License
CC0: Public Domain
Who Can Use It
- Banking Sector Professionals: To develop and implement customer retention programmes.
- Data Scientists and Analysts: For building predictive churn models and performing data analysis.
- Researchers: Studying customer attrition, financial behaviour, and predictive analytics in the banking domain.
- E-Commerce Services: To understand patterns of customer engagement and loyalty.
Dataset Name Suggestions
- Bank Customer Churn Prediction Dataset
- Credit Card Customer Attrition Data
- Banking Customer Retention Analytics
- Credit Card User Behaviour Dataset
- Customer Churn in Financial Services
Attributes
Original Data Source: Credit Card User Behaviour Dataset
QUALITY