Hackathon Key Code: 2775

Bank Marketing Campaign Analysis

Project Overview

This project focuses on analyzing and predicting customer responses to telephonic marketing campaigns conducted by a Portuguese banking institution. By identifying potential customers who are more likely to subscribe to a term deposit, the bank can optimize resources and improve the efficiency of its campaigns.

Dataset

The data pertains to direct marketing campaigns of a Portuguese bank and contains two datasets:

• Source: Link

Features Description

The dataset is divided into the following categories:

Bank Client Data

1. age: Age of the client (numeric)
2. job: Type of job
3. marital: Marital status
4. education: Level of education
5. default: Has credit in default?
6. balance: Average yearly balance in euros
7. housing: Has a housing loan?
8. loan: Has a personal loan?

Campaign-related Attributes

9. contact: Communication type
10. day: Last contact day of the month
11. month: Last contact month of the year
12. duration: Last contact duration in seconds

Other Attributes

13. campaign: Number of contacts performed during this campaign
14. pdays: Days since the client was last contacted in a previous campaign
15. previous: Number of contacts performed before this campaign
16. poutcome: Outcome of the previous marketing campaign

Objectives

1. Perform exploratory data analysis (EDA) to understand the dataset and relationships between variables.
2. Preprocess the data by handling missing values, encoding categorical variables, and scaling numerical features.
3. Build machine learning models to predict whether a client will subscribe to a term deposit.
4. Evaluate model performance using appropriate metrics and optimize for better accuracy.

Tools and Technologies

• Programming Language: Python
• Libraries: Pandas, NumPy, Plotly
• Visualization Tools: Excel, Power BI
• Development Environment: Jupyter Notebook / IDE of choice

Project Workflow

1. Data Preprocessing
2. Exploratory Data Analysis
3. Model Development
4. Model Optimization
5. Prediction

Evaluation Metrics

The following metrics will be used to evaluate model performance:

• Accuracy
• Precision
• F1-Score

Presentation

Powerpoint Presentation

Results

Results and insights from the analysis and models will be documented and visualized to demonstrate the effectiveness of the approach.

Acknowledgements

This is a Hackathon project initiated by Masai School, aimed at fostering innovation and collaboration among participants.

---

Team Members

Tanmay Tripathi

Ravi Kiran Venkata Sai Varma Gedela

Shreyashi Chavan