🧾 Marketing Campaign Analysis –5) Customer Behavior & Campaign Effectiveness

Analyzing customer demographics, purchasing behavior, and campaign response to improve marketing ROI using Python and Data Analytics..

---

📌 Table of Contents

• Overview
• Business Problem
• Dataset
• Tools & Technologies
• Project Structure
• Data Cleaning & Preparation
• Exploratory Data Analysis (EDA)
• Research Questions & Key Findings
• Data Insights
• Visualization
• How to Run This Project
• Final Recommendations
• Author & Contact

---

Overview

This project analyzes a retail marketing campaign dataset to understand customer behavior, spending patterns, and campaign effectiveness. The goal is to help businesses design targeted, data-driven marketing strategies that improve conversion rates and customer engagement.

The analysis focuses on: - Customer demographics - Product category spending - Campaign response behavior - Income and spending relationships - Customer segmentation indicators

---

Business Problem

Marketing campaigns often fail due to poor targeting and lack of customer insights. This project aims to answer: - Which customer groups respond best to marketing campaigns? - Which product categories generate the highest revenue? - How do income, family structure, and education impact spending? - Which customers should be prioritized for future campaigns?

---

Dataset

-Customer marketing campaign dataset (CSV format) -Contains information on: - Demographics (Age, Education, Marital Status, Income) - Household details (Kids, Teens) - Product-wise spending - Campaign responses - Purchase behavior

---

Tools & Technologies

• SQL (Common Table Expressions, Joins, Filtering)
• Python (Pandas, Matplotlib, Seaborn, SciPy,scikitlearn)
• Power BI (Interactive Visualizations)
• GitHub

---

Project Structure

vendor-performance-analysis/
│
├── README.md
├── .gitignore
├── requirements.txt
├── Marketing Campaign Analysis Report.pdf
│
├── notebooks/                  # Jupyter notebooks
│   ├── marketing_campaign.ipynb
|
├── dashboard/                  # Power BI dashboard file
│   └── marketing_campaign_dashboard.pbix

---

Data Cleaning & Preparation

• Removed missing values in Income

• Handled inconsistent categorical values

Created new features: - Total Spending - Age - Living_With (Partner / Alone)

• Converted data types for numerical analysis

• Removed unrealistic outliers where necessary

---

Exploratory Data Analysis (EDA)

Key Observations:

• Wine and meat products contribute the highest share of total spending

• Fruits and sweets show comparatively lower spending

• High-income customers tend to spend more across all categories

• Customers without kids show higher campaign acceptance rates

• Older customers generally spend more than younger groups

---

Research Questions & Key Findings

1. Which products drive the most revenue? → Wine and meat products dominate total spending.

2. Who responds best to campaigns? → High-income, fewer-children households.

3. Does income affect spending? → Strong positive correlation between income and total spending.

4. Which customers should be targeted? → Customers with high spending but low campaign exposure.

5. What is the role of family structure? → Customers living alone or with a partner spend more than larger families.

---

Data Insights

1. High-value customers are underutilized in campaigns.

2. Campaign response drops significantly for households with children.

3. Premium products should be marketed to high-income segments.

4. Low-spending categories can benefit from bundling strategies.

5. Personalized campaigns can significantly improve conversion rates.

---

Visualization

• The project includes visual analysis such as:
  • Product-wise spending distribution
  • Income vs total spending
  • Campaign acceptance by demographic groups
  • Correlation heatmaps
  • Spending patterns by age group

All visualizations are created using Matplotlib and Seaborn.

---

How to Run This Project

1. Clone the repository:

git clone https://github.com/yourusername/marketing-campaign-analysis.git

2. Install dependencies:

pip install -r requirements.txt

3. Open and run notebooks:
   • notebooks/marketing_campaign_analysis.ipynb
4. Open Power BI Dashboard:
   • dashboard/marketing_campaign_dashboard.pbix

---

Final Recommendations

• Focus campaigns on high-income and high-spending customers
• Reduce blanket marketing and adopt personalized targeting
• Promote high-margin products (wine, meat) aggressively
• Use bundling offers for low-performing product categories
• Optimize campaign frequency to avoid customer fatigue

---

Author & Contact

📧 Email: sharathspd1818@gmail.com 🔗 LinkedIn