Skip to main content

01 / Project · Power BI · Business Intelligence

Superstore Sales & Profitability Analysis

An interactive Power BI analysis of sales performance, profitability, customers, products, discounts, and modeled business scenarios.

View in Power BI

Microsoft sign-in may be required.

Context
Portfolio analysis · Superstore dataset
Role
Data analyst, end to end
Data window
9,994 rows · 2014–2017
Deliverable
Eight-page interactive Power BI report
Exhibit 01 — Executive overview of the eight-page Power BI report

What the business learned

Total Sales

$2.30M

Gross Profit

$286.40K

Gross Margin

12.47%

Orders

5,009

Customers

793

Quantity

37,873

Sales by region

West: $725.46K. East: $678.78K. Central: $501.24K. South: $391.72K.

West and East lead the four-region sales view, while South records the lowest sales in the dataset.

Gross profit by category

Technology: $145.45K. Office Supplies: $122.49K. Furniture: $18.45K.

Technology and Office Supplies account for most recorded gross profit; Furniture is materially lower despite substantial sales.

Business Insights

Sales growth and margin movement tell different stories

The overview shows 2017 sales 20.4% above 2016, while gross margin is 0.7 percentage points lower. The dashboard therefore keeps sales, profit, and margin together when assessing performance.

Furniture sales do not translate into comparable profit

Furniture records about $742K in sales but only $18.45K in gross profit, well below Technology and Office Supplies. This highlights pricing, cost, product mix, and discounts as areas for further investigation.

A small set of products creates outsized downside

The product view identifies ten products with the lowest gross profit; the Cubify CubeX 3D Printer Double Head Print records the largest loss at about $8.88K.

Sales are concentrated geographically and by segment

West and East are the strongest sales regions, California is the leading state, and Consumer contributes 50.56% of total sales. These are concentration signals, not proof of cause.

Project Evidence

  • Consolidated 9,994 transaction rows into an eight-page decision path from overview to scenario analysis.
  • Separated sales scale from profitability so high-revenue but low-margin areas remain visible.
  • Made product losses, regional concentration, customer contribution, and discount scenarios explorable through dedicated report pages.

Scenario analysis

  • The report uses a discount-adjustment parameter ranging from −20% to +20%, with 0% as the current baseline shown in the final screenshot.
  • Scenario cards and comparison charts show modeled sales, gross profit, gross margin, and profit impact alongside current performance.
  • These outputs are modeled comparisons rather than forecasts or guaranteed business outcomes.

Recommendations

  • Set discount limits by product and sub-category to help protect profitability.
  • Review pricing, costs, and discounts for products that consistently generate losses.
  • Prioritize inventory and marketing review for products with strong sales and healthy margins.
  • Focus inventory and campaign planning on West and East, especially top-performing states.
  • Target top customers and the Consumer segment with retention and cross-selling tests.
  • Track sales, gross profit, and gross margin together when evaluating performance.

The Business Problem

This portfolio project turns the Sample Superstore dataset into an eight-page Power BI report covering executive performance, sales, profitability, products, customers, geography, business insights, and scenario analysis.

The report combines a prepared data model, reusable DAX measures, year-over-year comparisons, interactive filters, report navigation, and a discount what-if parameter.

The source contains 9,994 transaction rows across products, customers, segments, states, regions, discounts, sales, and profit. In row form, it is difficult to see where strong sales translate into healthy profit and where they do not.

The analytical objective was to create a guided report that moves from overall performance to product, customer, geographic, discount, and scenario-level questions without presenting the exercise as a real client engagement.

Objectives

  • Track sales, profit, margin, orders, customers, quantity, and year-over-year movement
  • Compare performance across categories, products, customer segments, states, and regions
  • Identify loss-making products and low-margin areas for further review
  • Model how discount adjustments change scenario sales and gross profit

Business questions

  • How are sales and gross profit changing over time?
  • Which categories, sub-categories, and products generate the most sales and profit?
  • Which products and sub-categories generate losses?
  • Where is profitability weak despite substantial sales?
  • How do discount levels relate to gross profit across sub-categories?
  • Which customer segments, customers, states, and regions contribute the most sales?
  • How do modeled discount adjustments change scenario sales, gross profit, and margin?

The Approach

Dataset

  • Sample Superstore CSV with 9,994 rows and 21 fields
  • Order dates cover 2014–2017
  • Fields include orders, customers, segments, geography, products, sales, quantity, discount, and profit
  • The report uses 5,009 distinct orders, 793 customers, and 1,862 products

Data Cleaning

  • Loaded the transaction source through Power Query
  • Applied date logic to support year, month, and year-over-year comparisons
  • Organized product, customer, geography, discount, sales, and profit fields for consistent filtering
  • Kept modeled scenario outputs separate from current recorded performance

Analysis Process

  • Data → Power Query → Data Model → DAX → Analysis → Interactive Power BI Report
  • Created reusable measures for sales, gross profit, gross margin, orders, customers, quantity, pricing, discounts, and prior-year comparisons
  • Built a −20% to +20% discount-adjustment parameter with current-versus-scenario sales, gross profit, margin, and profit-impact views
  • Added page navigation and shared filters for date range, category, segment, and region
  • Validated portfolio figures against the final report screenshots and source CSV

Dashboard Screenshots

Sales Analysis — sales trend, top sub-categories, and an interactive decomposition of sales drivers
Profit & Pricing — gross profit, margin, cost, discount, and sub-category profitability
Product Analysis — portfolio breadth, unit economics, top sellers, and loss-making products
Customer & Geography — customer value and geographic concentration across regions and states
Scenario Analysis — compare current results with modeled discount adjustments from −20% to +20%
Business Insights — documented findings and recommended actions kept in separate columns
Home — guided navigation to the seven analytical report pages
Microsoft Power BIPower QueryDAXData ModelingBusiness Intelligence

Field Notes

Lessons from this project you can use in your own work:

  1. Pair sales with profit and margin. A revenue leaderboard can hide categories or products that contribute little profit or generate losses.

  2. Use cautious language around discounts. The dashboard shows an association with weaker profitability in parts of the data, but the report does not establish causality.

  3. Keep what-if assumptions visible. A scenario is easier to interpret when the selected adjustment, current baseline, and modeled outputs appear on the same page.

  4. Separate findings from recommendations. Readers should be able to see which statements describe the data and which suggest a next action.

Next project: Salla Call CenterView ResumeDiscuss this project on WhatsAppBack to Projects