This project analyzes end-to-end user behavior and conversion performance for an e-commerce platform using Python for data analysis and Power BI for interactive dashboards. The goal is to understand how users move through the funnel (Browse → Add to Cart → Checkout → Purchase), identify major drop-off points, and generate actionable business insights.
- Where do users drop off most in the purchase funnel?
- What is the overall and stage-wise conversion rate?
- Which channels, devices, and regions generate the most revenue?
- How does user behavior vary by device and product category?
- What actions can improve checkout completion and engagement?
-
Total Users: 10,000
-
Funnel Stages: Browse, Add to Cart, Checkout, Purchase
-
Time Granularity: Daily
-
Dimensions:
- Channel (Email, Google Ads, Social Media, Organic)
- Region (East, North, South, West)
- Device (Desktop, Mobile, Tablet)
- Product Category
- Python: pandas, numpy, matplotlib (EDA & data preparation)
- Power BI: Data modeling, DAX, dashboarding
- SQL: Aggregations & validation
- GitHub: Version control & documentation
- Overall conversion rate is 10.8%, indicating strong top-of-funnel traffic but weak checkout completion.
- Checkout → Purchase is the biggest drop-off stage
- Paid channels (Email & Google Ads) outperform Organic in revenue
- Desktop users show the highest drop-off rate
- Electronics and Fashion are the top revenue-driving categories
- High bounce rate (~89%) signals low landing-page engagement
- Simplify checkout flow to reduce friction
- Introduce cart-abandonment retargeting campaigns
- Optimize landing pages to reduce bounce rate
- Invest more in high-performing paid channels
- Improve desktop UX based on drop-off diagnostics
- Track returning users to measure long-term retention
⭐ If you found this project useful, feel free to star the repository!