I have a large backlog of raw e-commerce sales exports that need to be turned into clean, analysis-ready data and concise management reports. The work begins with rigorous data cleaning—deduplicating transactions, fixing date and currency formats, and standardising product identifiers. Once the data is spotless, I want it aggregated by product, category, customer and time period, then transformed into a tidy, relational structure that slots neatly into any BI tool. From this refined dataset I need two specific report packs: • Customer segmentation – highlight key segments by purchase frequency, lifetime value and basket mix. • Inventory report – surface fast and slow movers, current stock positions and days-of-stock projections. Please keep everything reproducible. A Python + pandas / SQL workflow is ideal, but I’m open to any open-source stack you prefer—just document your steps so I can rerun the pipeline with fresh files. Efficiency matters: the full dataset runs into a few million rows. Deliverables 1. Cleaned master dataset (CSV or Parquet) 2. Aggregated and transformed tables ready for analysis 3. Customer segmentation report (interactive dashboard or PDF) 4. Inventory report (interactive dashboard or PDF) 5. Well-commented script or notebook with a short README explaining setup and execution I’ll send a sample extract as soon as we agree on the approach; feel free to flag any clarifications you need before diving into code.