2025Local
E-commerce Sales Analysis
- Python
- Pandas
- NumPy
- Plotly
- Jupyter
Overview
Funnel analysis, RFM customer segmentation and trend analysis on an e-commerce store's sales and visit data. The analysis code lives in Python modules separate from the notebooks; the data is a synthetic dataset generated by scripts, and the results become interactive Plotly charts.
01 · Problem
Raw e-commerce data does not show at which step visitors abandon a purchase, which customers are the most valuable, or how sales change over time.
02 · Solution
I generated a year of session, order and customer data synthetically with Python scripts and split the analysis into reusable classes separate from the notebooks (FunnelAnalyzer, RFMAnalyzer, TrendAnalyzer). I computed the view → cart → checkout → purchase funnel, quartile-based RFM scoring and daily/monthly conversion trends with Pandas and turned them into interactive Plotly charts.
03 · Outcome
The funnel, RFM and trend analysis method was built end to end; seven interactive charts and an executive summary can be regenerated from code. Because the data is synthetic, the rates are not findings about a real store; the code is ready to run on a store's own export or a public e-commerce dataset.