Rachel Maro
Back to work

Case study · Independent demonstration

Sales & Profitability for a fictional Tanzanian homeware retailer

Synthetic data, January–December 2025: 1,200 sale records, 6 products, 3 sales channels, 4 cities. Every figure on this page is simulated.

RevenueSimulated
TZS 237.8M
Gross profitSimulated
TZS 75.7M
ContributionSimulated
TZS 68.6M
Contribution marginSimulated
28.9%

Contribution = revenue less product costs, seller-paid delivery and channel fees. Excludes overhead and tax.

Interactive dashboard

By productSimulated

Six products, Jan–Dec 2025, Contribution (TZS), simulated data
NameContribution (TZS)
Cookware setTZS 26.0M
Rice cookerTZS 12.9M
BlenderTZS 10.2M
KettleTZS 7.4M
Storage setTZS 6.5M
ThermosTZS 5.8M
Six products, Jan–Dec 2025 · Contribution (TZS) · sorted high to low

Product chart now showing Contribution (TZS)

By channelSimulated

Three sales channels, Jan–Dec 2025, Contribution margin (%), simulated data
NameContribution margin (%)
Store33.7%
WhatsApp30.7%
Marketplace11.7%
Three sales channels, Jan–Dec 2025 · Contribution margin (%) · sorted high to low

Channel chart now showing Contribution margin (%)

Monthly trend, 2025Simulated

Monthly revenue rises from TZS 13.2M in January to TZS 27.0M in December 2025; contribution ranges from TZS 4.1M to TZS 7.5M. Simulated.0M10M20MJanFebMarAprMayJunJulAugSepOctNovDec
Revenue (TZS)Contribution (TZS, dashed)
View monthly data table
MonthRevenueContribution
JanTZS 13.2MTZS 4.1M
FebTZS 17.8MTZS 5.6M
MarTZS 18.7MTZS 5.8M
AprTZS 19.3MTZS 6.2M
MayTZS 19.2MTZS 5.9M
JunTZS 18.8MTZS 5.8M
JulTZS 18.1MTZS 5.1M
AugTZS 20.1MTZS 5.6M
SepTZS 22.1MTZS 5.9M
OctTZS 22.4MTZS 5.7M
NovTZS 21.3MTZS 5.4M
DecTZS 27.0MTZS 7.5M

The website displays pre-aggregated results; metric switches do not cross-filter the dataset.

Business question

Which products and sales channels contribute the most after direct costs — and where might the retailer test changes to protect margin?

Methods

Generated clean synthetic sales records, Excel formulas including SUMIFS, and formula-linked charts; reproducible SQLite queries and a Python validation script.

Excel is the primary tool. SQL and Python totals match the workbook. No real-world data cleaning was involved, and the workbook contains no PivotTables.

Contribution and contribution margin were compared across products and channels, alongside the monthly revenue trend.

Findings

  • Cookware set delivers the largest contribution: TZS 25.97M (simulated).
  • Storage set has the highest contribution margin at 38.9%, despite lower revenue (simulated).
  • Marketplace margin is 11.7%, versus 33.7% in Store and 30.7% on WhatsApp. This gap is driven partly by invented fee and discount assumptions in the synthetic data.

Recommendations

These are proposed tests, not achieved impact:

  • Test reduced discounting or adjusted pricing on Marketplace listings and track margin.
  • Trial promoting Storage sets alongside Cookware on Store and WhatsApp channels.
  • Review Rice cooker cost or price, given its high revenue but lower margin.

Limitations

  • The dataset is synthetic; patterns reflect generation assumptions, not a real market.
  • Channel fees and discounts were invented, which strongly shapes the Marketplace result.
  • Overhead and tax are excluded, so contribution is not net profit.
  • The website displays pre-aggregated results; metric switches do not cross-filter the dataset.

Source & attribution

Original synthetic dataset generated with ChatGPT on 10 October 2026 (seed 20261010). No external or workplace records were used.

Downloads