Dark Mode
Bank Client Phone Marketing Results
Finance & Banking Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
The data originates from direct marketing campaigns managed by a Portuguese banking institution. These campaigns primarily utilized phone calls to engage clients. The core objective of this data is to determine whether a client subscribed to a bank term deposit product. The records provide detailed information on client demographics, bank-related variables (such as balance and loan status), and specific metrics detailing the current and previous marketing interactions.
Columns
The dataset comprises 17 input and output variables:
Bank Client Data (8 variables):
- age: The client's age (numeric).
- job: The client's job type (categorical, including "admin.", "blue-collar", "management", "unknown", "unemployed", "housemaid", "entrepreneur", "student", "self-employed", "retired", "technician", "services").
- marital: The client's marital status (categorical: "married", "single", "divorced"; noting "divorced" includes widowed clients).
- education: The client's education level (categorical: "unknown", "secondary", "primary", "tertiary").
- default: Binary indicator of whether the client has credit in default ("yes", "no").
- balance: The average yearly balance, measured in euros (numeric).
- housing: Binary indicator of whether the client has a housing loan ("yes", "no").
- loan: Binary indicator of whether the client has a personal loan ("yes", "no").
Last Contact Data (4 variables):
- contact: The communication type used in the last contact (categorical: "unknown", "telephone", "cellular").
- day: The day of the month of the last contact (numeric).
- month: The month of the year of the last contact (categorical, e.g., "jan", "feb", ..., "dec").
- duration: The duration of the last contact, measured in seconds (numeric).
Other Attributes (4 variables):
- campaign: The total number of contacts performed during this campaign for the client (numeric, includes the last contact).
- pdays: The number of days passed after the client was last contacted from a previous campaign (numeric; -1 indicates the client was not previously contacted).
- previous: The total number of contacts performed before this specific campaign for the client (numeric).
- poutcome: The outcome of the previous marketing campaign (categorical: "unknown", "other", "failure", "success").
Output Variable (1 variable):
- y: The target variable, indicating if the client subscribed to a term deposit (binary: "yes", "no").
Distribution
The data is structured as a tabular file, typically provided in CSV format, with a file size of 3.7 MB. It contains 17 columns and 45,211 valid records. The majority of columns, including 'Age', 'Job', and 'Balance', show zero missing values. The expected update frequency for the underlying data is annually.
Usage
This resource is best suited for supervised learning and analytical tasks within the financial sector. Ideal applications include:
- Developing and testing classification models to predict client propensity for subscribing to bank term deposits.
- Conducting statistical analysis to identify key drivers (client characteristics or campaign tactics) influencing successful marketing outcomes.
- Grouping clients through clustering techniques based on their behavioural and demographic features.
- Benchmarking the performance of direct marketing efforts, particularly those conducted via telephone.
Coverage
The scope covers marketing activities executed by a banking institution in Portugal. The data encompasses client demographics (with ages ranging from 18 to 95), detailed financial status, and temporal information regarding marketing efforts. Contact months span the entire year, with 'may' being the most frequent contact month.
License
CC0: Public Domain
Who Can Use It
- Financial Modellers: Individuals focused on building reliable models for customer lifetime value and churn prediction.
- Marketing Strategists: Professionals seeking data-driven insights to refine target audience selection and optimise resource allocation for direct campaigns.
- Academic Researchers: Users studying the effectiveness of behavioural targeting and prediction in bank product uptake.
Dataset Name Suggestions
- Portuguese Bank Term Deposit Marketing Data
- Bank Client Phone Marketing Results
- Campaign Subscription Prediction Data
- Financial Services Direct Marketing Records
Attributes
Original Data Source: Bank Client Phone Marketing Results
QUALITYLoading...