Fashion Intelligence Series | Module 5 of 6

Collection planning:
Fewer SKUs, more margin

How a cannibalization network identifies the 400 SKUs out of 1,800 as candidates for the assortment review, with only 3% revenue loss but up to 18% less overstock and €0.78M margin improvement.

Model scenario: fictional fashion company

This module is part of a six-part model calculation about a fictional mid-sized fashion company (1,800 SKUs, 18 markets). All figures, datasets, model metrics, and euro amounts are entirely fictional: they illustrate the methodology and the kind of effect achievable. They are not results of real clients and not a performance promise. What values are achievable on your real data is established only in a pilot project.

01 The problem: planning 1,800 SKUs when 400 are unnecessary

Why a wide assortment does not automatically mean more revenue

More SKUs = more choice = more revenue? Our analysis shows: 22% of SKUs generate 78% of revenue. The remaining 78% cannibalize one another, tie up warehouse capacity, and generate overstock. The model identifies which SKUs your assortment needs and which are candidates for review in the next assortment round.

02 Model: assortment optimization with a cannibalization network

-22%
SKUs in assortment
-3%
Revenue impact
-18%
Overstock
€0,78M
Margin improvement
SKU contribution: revenue share vs. overstock share
↳ 400 fewer SKUs, nearly identical revenue

The model identifies 400 SKUs as removal candidates, which together generate only 3% of revenue but cause 18% of overstock. If approved in the assortment round, overstock drops by up to 18%, at a cost of around 3% of revenue. The €0.78M margin improvement is a net figure: saved production, warehousing, and markdown costs minus foregone contribution margin, an assumption of the model calculation anchored in the Pareto norm (around 20% of SKUs account for around 80% of revenue). The model does not replace the assortment decision. It provides the data foundation for an informed discussion in the buying and design team. The final decision additionally considers brand positioning, supplier relationships, and range width.

03 Next steps for your brand

① Assortment analysis

All 1,800 SKUs through the cannibalization network. Report: top performers, cannibalizers, candidates for removal.

② Pilot: 1 collection

Next season: optimized assortment in 3 pilot markets vs. standard assortment. A/B at market level.

③ Design feedback

Data-driven recommendations for your design team: which silhouettes, colors, and price points are missing from the assortment?

All 6 modules: AI in fashion