Analyses sales, margin and stock data to optimise the assortment.
Developed in Germany · Hosted in the EU or on-premises
Delivered together with
Sovereign hosting in Germany, single-tenant from the first user.
Legal, tax and compliance expertise for legally sound deployment.
Advisory and implementation for the public sector, starting with the AI readiness assessment.
Sell-through figures sit in the merchandise management system, purchase terms in the ERP, stock per store somewhere else again. For the assortment review, category management pulls three extracts and builds a spreadsheet, adding markdowns and advertising allowances by hand. By the time the spreadsheet is ready, half the season has gone, and in the end it is experience that decides which items are slow sellers.
Twelve months of sell-through, margin and stock cover sit side by side for every one of the 1,240 items, and the assortment review works from 38 named candidates rather than a hunch, delivering 5 to 15% higher margin.
The 5 to 15% higher margin is this agent's headline figure. The 1,240 item numbers and the four days spent building the spreadsheet reflect a typical assortment review in one category; neither figure comes from an actual count.
The agent reads twelve months of sell-through from the merchandise management system and sets purchase terms, markdowns and advertising allowances alongside it. Every item number gets a contribution margin calculated the same way.
Contribution margin list, household category, 1,240 item numbers, 12 monthsThe agent ranks the items by contribution margin and stock cover and flags every line with no movement. It records seasonal patterns separately, so that winter stock does not show up as a slow seller in summer.
47 items with no sales for 26 weeks, 9 of them with a seasonal patternThe agent lines up delisting and reorder candidates with contribution margin, stock cover and a prior-year comparison. The review goes through the list line by line.
sortimentsvorschlag_haushalt_kw34.xlsx, 38 delisting and 22 reorder candidatesIt presents the candidates with contribution margin and stock cover. The category head signs off the delisting, and master data management books it.
A key item can stay on the shelf despite a weak margin because customers expect to find it there. Category management makes that call in the assortment review.
The new terms for the household category only apply once they are booked in the ERP. Until then it shows the old value and flags it; category management recalculates once the deal is closed.
Connected systems
Operations
A pilot typically runs on your own data within 4 to 6 weeks. The agent connects to your existing systems rather than running as a separate, parallel environment.
EU cloud or private cloud. Processing is GDPR-compliant and models are never trained on your data. Details in the Trust Center.
It is based on experience from comparable projects and process benchmarks, not a commitment. We work out the realistic effect for your organisation during the assessment before the pilot.