Dark Mode
Churn Modelling Dataset
Agent Simulation Data
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset provides detailed information about customers of a company, with the primary objective of enabling customer churn prediction using advanced analytical methods such as Deep Learning Artificial Neural Networks. It contains various customer attributes that can be used to identify patterns and predict which customers are likely to leave, offering valuable insights for business strategy and customer retention efforts.
Columns
- RowNumber: A sequential number assigned to each row.
- CustomerId: A unique identifier for each customer.
- Surname: The surname of the customer.
- CreditScore: The customer's credit score, ranging from 350 to 850.
- Geography: The country the customer belongs to, with three unique countries represented.
- Gender: The customer's gender, either Male or Female.
- Age: The customer's age, with a range of 18 to 92 years.
- Tenure: The duration, in years, of the customer's bond with the company, ranging from 0 to 10 years.
- Balance: The amount of money held by the customer, ranging up to approximately 251,000.
- NumOfProducts: The number of products the customer owns, ranging from 1 to 4.
- HasCrCard: Indicates whether the customer possesses a credit card (1 for Yes, 0 for No).
- IsActiveMember: Indicates how active the customer is (1 for active, 0 for inactive).
- EstimatedSalary: The customer's estimated salary, ranging up to approximately 200,000.
- Exited: The target variable, indicating whether the customer has exited (left) the company (1 for Exited, 0 for Stayed).
Distribution
The dataset is provided in a CSV format and measures approximately 684.86 KB. It comprises 14 columns and contains 10,000 valid records. All columns are fully populated, with 0% mismatched or missing values across the dataset. The
RowNumber column has values ranging from 1 to 10,000, with a mean of 5,000. The CustomerId values are large, unique identifiers.Usage
This dataset is ideally suited for developing and training Deep Learning models for customer churn prediction. It can be utilised for:
- Building predictive models to identify customers at risk of churn.
- Analysing the factors that contribute to customer attrition.
- Developing customer retention strategies based on predictive insights.
- Academic research in customer behaviour and predictive analytics.
Coverage
The dataset's geographic scope covers three distinct countries, with France being the most frequent origin for customers, accounting for 50% of the data. Demographically, the dataset includes customers with ages ranging from 18 to 92 years, with an average age of 38.9 years. The gender distribution shows approximately 55% Male and 45% Female customers. Financial aspects are covered through credit scores (350-850) and estimated salaries (up to 200,000), alongside account balances. The tenure with the company spans from 0 to 10 years.
License
CC0: Public Domain
Who Can Use It
This dataset is particularly beneficial for:
- Data Scientists and Machine Learning Engineers: For building and validating churn prediction models.
- Business Analysts: To understand customer behaviour and inform strategic decisions related to customer retention.
- Companies: Seeking to reduce churn and improve customer loyalty.
- Researchers: Studying customer dynamics and predictive analytics.
Dataset Name Suggestions
- Customer Churn Prediction Data
- Churn Modelling Dataset
- Bank Customer Churn Data
- Customer Exit Prediction
Attributes
Original Data Source: Customer Churn Prediction Data
QUALITY