A data-driven analysis to segment customers based on behavior and spending patterns, enabling personalized marketing strategies and improved customer retention.
A company wants to better understand its customers to improve marketing effectiveness and maximize revenue.
Key questions:
- Can customers be grouped based on purchasing behavior?
- Which customer segments are most valuable?
- How can marketing strategies be tailored for each segment?
Segment customers into meaningful groups using data analysis and provide actionable insights for targeted marketing and customer engagement.
Customer dataset containing:
- CustomerID → Unique identifier
- Gender → Male/Female
- Age → Customer age
- Annual Income (k$) → Income level
- Spending Score (1–100) → Spending behavior
- Cleaned dataset and handled inconsistencies
- Selected relevant features for clustering
- Analyzed distributions of age, income, and spending score
- Identified initial patterns in customer behavior
- Applied K-Means Clustering algorithm
- Determined optimal number of clusters using the Elbow Method
- Interpreted each cluster based on income and spending patterns
- Compared behavior across segments
- Identified distinct customer segments based on income and spending behavior
- High-income, high-spending customers contribute significantly to revenue
- Mid-income customers show potential for upselling
- Low-spending segments require engagement strategies
- 🎯 Target high-value customers with premium offerings
- 📈 Upsell mid-value customers through personalized campaigns
- 📉 Engage low-spending customers using discounts and promotions
- 📊 Use segmentation to drive personalized marketing strategies
- Python
- Pandas
- NumPy
- Scikit-learn
- Matplotlib
- Seaborn
git clone https://github.com/Harshu2326/Customer-Segmentation-Project.git
cd Customer-Segmentation-Project
pip install -r requirements.txt