This project involves analyzing a bank marketing dataset to predict the success of telemarketing campaigns. The dataset contains 45,211 observations with 18 features. The analysis includes various visualizations and insights drawn from the data to understand customer behavior and campaign effectiveness.
The dataset includes the following features:
- Age: Numeric
- Job: Type of job (12 categories)
- Marital: Marital status (3 categories)
- Education: Education level (4 categories)
- Housing: Has a housing loan? (Yes, No)
- Duration: Contact duration with a customer
- Loan: Has a personal loan? (Yes, No)
- Contact: Contact communication type
- Day: Last contact day of the week
- Month: Last contact month of the year (12 categories)
- Campaign: Number of contacts performed during this campaign and for this customer
- Pdays: Number of days since the customer was last contacted from a previous campaign
- Previous: Number of contacts made before this campaign
- Poutcome: Outcome of the previous marketing campaign (failure, unknown, other, success)
- Y: Desired outcome, whether the customer subscribed or not
- Job Field: Most participants were from blue-collar jobs.
- Marital Status: More married people participated than single or divorced.
- Education: Majority had secondary education.
- Housing Loan: Most customers did not have a housing loan.
- Personal Loan: Most customers did not have a personal loan.
- Contact Type: Majority preferred cellular communication.
- Last Contact Day: Varied, with some peak days like the 20th.
- Last Contact Month: May had the highest number of contacts.
- Campaign Contacts: Multiple contacts were made during campaigns.
- Previous Contacts: Prior contacts influenced current campaign success.
- Subscription Outcome: Duration of contact significantly impacted subscription decisions.
The report includes various graphs representing distributions and relationships among features, providing a clear understanding of customer behavior and campaign effectiveness.
Customer decisions in bank telemarketing are influenced by factors like the quality of the marketing campaign, contact duration, and whether the customer has a loan. Number of contacts alone does not determine subscription success.