E-commerce Customer Segmentation Model -- 2

I’m looking to turn our raw e-commerce data into a practical customer-segmentation model and a set of clear, interactive visuals. The core of the job is to build a predictive model in Python that groups customers by meaningful behaviour traits, then surface those insights through tidy Excel summaries and a polished Power BI dashboard my team can explore on their own.

Here’s how I picture the flow:

• You’ll clean and shape the sales, product and customer tables I’ll provide (CSV/Excel).
• Build and validate a clustering or classification approach that reliably separates customers into actionable segments. I’m open to K-means, hierarchical, or something more advanced if it improves accuracy and interpretability.
• Translate the key metrics of each segment—spend, frequency, product mix, lifetime value—into an Excel sheet my finance team can download.
• Design a live Power BI report that lets users filter by date range and segment, showing purchase patterns, segment growth and any red-flag behaviour.

Acceptance criteria
• Python notebook (.ipynb) or script with well-commented code, ready to rerun on future data drops.
• Clean data set and segment labels saved back to Excel.
• Power BI file (.pbix) with interactive visuals and at least three pages: Overview, Segment Deep Dive and Trend Analysis.
• A brief read-me describing model choice, evaluation metrics and how to refresh everything.

If you have examples of similar segmentation work, especially in retail or e-commerce, please share a link or screenshot so I can gauge fit quickly.