Dark Mode
Financial Churn Analysis Data
Finance & Banking Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset is designed to predict customer churn within a bank. Understanding why clients decide to leave is crucial for financial institutions, as retaining existing customers is often more cost-effective than acquiring new ones. This data enables the development of loyalty programmes and retention campaigns, aiming to minimise customer attrition.
Columns
- RowNumber: Corresponds to the record number and has no effect on the output.
- CustomerId: Contains random values and does not influence a customer's decision to leave the bank.
- Surname: The customer's surname has no impact on their decision to exit the bank.
- CreditScore: Can affect customer churn; a higher credit score suggests a lower likelihood of a customer leaving the bank.
- Geography: A customer’s location can influence their decision to leave the bank.
- Gender: It is interesting to explore whether gender plays a role in a customer leaving the bank.
- Age: Highly relevant, as older customers are less likely to leave their bank than younger ones.
- Tenure: Refers to the number of years the customer has been a client of the bank. Generally, clients with longer tenure are more loyal and less likely to churn.
- Balance: A strong indicator of customer churn; individuals with higher account balances are less likely to leave the bank compared to those with lower balances.
- NumOfProducts: Denotes the number of products a customer has purchased through the bank.
- HasCrCard: Indicates whether or not a customer possesses a credit card. Customers with a credit card are less likely to leave the bank.
- IsActiveMember: Active customers show a reduced propensity to leave the bank.
- EstimatedSalary: Similar to balance, individuals with lower estimated salaries are more inclined to leave the bank than those with higher salaries.
- Exited: This binary variable signifies whether or not the customer left the bank.
Distribution
The dataset is provided in a CSV format, specifically as 'churn.csv', with a file size of 684.86 kB. It contains 10,000 valid records across all 14 columns. For instance, the 'RowNumber' column ranges from 1 to 10,000, with 1,000 entries per bin of 1,000 row numbers. The 'CreditScore' data ranges from 350 to 850, with a mean of 651. 'Age' spans from 18 to 92 years, with a mean of 38.9. 'Balance' ranges from 0 to approximately 251,000, with a mean of 76,500.
Usage
This dataset is ideal for:
- Developing predictive models to forecast customer churn in the banking sector.
- Designing and implementing customer loyalty programmes.
- Crafting targeted customer retention campaigns.
- Conducting analytical studies to identify key factors influencing customer decisions to leave a bank.
Coverage
The dataset includes customer data from three unique geographical locations, with France accounting for 50% of the entries. Demographic information covers customer gender (55% Male, 45% Female) and age, ranging from 18 to 92 years. Specific time range coverage for the data is not specified in the provided information.
License
CC0: Public Domain
Who Can Use It
- Banks and financial institutions: To proactively identify at-risk customers and implement retention strategies.
- Data scientists and machine learning engineers: For building and evaluating churn prediction models.
- Business analysts and strategists: To gain insights into customer behaviour and inform business decisions regarding customer lifetime value.
Dataset Name Suggestions
- Bank Customer Churn Predictor
- Financial Churn Analysis Data
- Customer Retention in Banking Dataset
- Bank Client Exit Prediction
Attributes
Original Data Source: Financial Churn Analysis Data
QUALITY