Protocol_Method — E-Commerce Sales Analysis

The problem

Standard AI analysis often ignores dirty data, leading to inflated revenue figures and flawed business strategies. Developers and store owners frequently make decisions based on uncleaned exports that include refunds, duplicates, and mixed currencies.

What it does

• Performs rigorous data cleaning by removing duplicates, excluding refunds/cancellations, and normalizing multi-currency exports into a single base currency.
• Identifies outliers and impossible values in price or quantity to ensure the dataset is statistically sound.
• Distinguishes between high-volume products and high-margin products to reveal hidden profitability leaks.
• Calculates repeat purchase rates and Customer Lifetime Value (CLV) to assess long-term business health.
• Generates an executive summary with three prioritized recommendations focused on action, impact, and effort.

Frameworks & tools

Optimized for Shopify, Etsy, Amazon Seller Central, and WooCommerce exports. Works with CSV and Excel formats using Python-based execution for data processing.

Why this beats prompting it yourself

Generic prompts often fail to account for ecommerce-specific traps like 'returned' status orders inflating GMV. This skill enforces a strict senior analyst protocol that prioritizes data integrity and margin reality over surface-level metrics.

Use cases

• Conducting monthly or quarterly performance audits for Shopify or WooCommerce stores.
• Diagnosing sudden drops in net margin or unexpected changes in revenue.
• Preparing investor-ready sales reports with verified, cleaned data.
• Identifying specific products that require repricing due to low margins despite high sales volume.

Known limitations

Cannot calculate margins if unit costs are missing from the export. Channel profitability analysis is limited if acquisition costs (CAC) are not provided in the source file.