01
Executive Overview
Management view of revenue, sessions, orders, conversion, refund risk and previous-period context.
Power BI portfolio case study
AI-assisted Power BI dashboard for e-commerce growth
A five-page reporting framework connecting sessions, orders, revenue, product performance and refund risk—designed through an AI-assisted, human-led workflow.
Portfolio project using the Maven Fuzzy Factory dataset. Not a production deployment or client result.
The challenge
Turn separate operational signals into one decision story.
E-commerce reporting often separates traffic, conversion, commercial performance and refund risk. This project organized them into one sequence:
SessionsOrdersRevenueProductsRefundsManagement insights
Claude Design workflow
Move visual decisions earlier—then review every assumption.
Claude Design was used to explore composition, KPI hierarchy, spacing, color direction and visual density before the Power BI build. The mockup was treated as a design hypothesis, not analysis or implementation.
- Define business questions and page purpose.
- Generate a visual direction and multi-page mockups.
- Review fields, categories, metric grain and wording against the real model.
- Revise the direction, then rebuild and validate it in Power BI.
What the first mockup got wrong
Fast visual exploration still needs a rigorous correction loop.
- Unsupported source labels were replaced with categories present in the data.
- A Tablet category was removed because the model only supported Desktop and Mobile.
- Placeholder-like funnel values were replaced by measures tied to a session-level funnel table.
- Simplified product labels were replaced with the dataset's real product names.
- Causal and predictive wording was removed from the insight layer.
Final Power BI implementation
A five-page reporting system built around business questions.
Power Query, relationships, DAX, previous-period logic, metric grain, filter context and final interpretation remained human-led.
02
Marketing & Conversion
Traffic quality, source and device performance, and the session-level funnel.
03
Sales Performance
Order- and item-level commercial performance, product revenue, gross profit and margin.
04
Products & Refund Analysis
Product contribution, sales volume, margin quality and refund risk at the correct grain.
05
Insight & Management Actions
A plain-language reading layer based on validated measures—not a forecast or automated decision system.
Results & learnings
AI accelerated design exploration. BI judgment made it reliable.
Reusable outcome. A visual system, five-page dashboard architecture, documented measures and repeatable design-to-build workflow.
Clear responsibility boundary. AI supported visual exploration and a theme starting point; modeling, DAX, validation and business interpretation stayed human-led.
Practical lesson. Every AI-generated label, number, insight and visual assumption needs review against the semantic model and business context.
Work with HYDRADATA