Master data & classification
Class and attribute models, value formats and mandatory fields — the structure that makes items comparable.
- Class and attribute design
- Naming rules
- Change request governance
empty filled in SAP found by enrichment
Engineering solutions for data governance
We combine master data and SAP MDG expertise with data engineering and large language models. We enrich attributes, normalize values, find duplicates and analogs, and check new records before they are created — with a source for every value and a measurable result for every class.
Case study: electrical MRO catalog of an industrial holding — 8,008 items in 44 SAP MDG classes.
What we do
From the class model to the data platform underneath it: we design the rules, build the engineering and measure the result on your data — not on a demo.
Class and attribute models, value formats and mandatory fields — the structure that makes items comparable.
How classification lives in your master system and the systems around it.
Models find and verify values instead of inventing them.
One catalog to buy, store and repair by — across classes where the same part was set up differently.
Rules, metrics and quality control at every step of the data lifecycle.
Storage, formats and search for large data — and language models that run on your own servers.
Principles
You see where every value came from — and you decide what goes into your master system.
Every value has a source and a confidence: SAP, item name, designation, standard or a catalog page.
SAP values are never overwritten. A disagreement is logged as a conflict, with the alternative and its source alongside.
AI prepares proposals and a review queue; your engineers and data stewards approve.
Attribute and record completeness before and after — for every class.
The model fits your security requirements: deployed on your infrastructure, or external models where they are allowed.
Case study · Industrial holding
The holding needed a materials catalog people could search, compare and buy from. Two procurement groups — electric motors and wiring accessories — held 8,008 items in 44 SAP MDG classes, yet only 226 of 3,941 active records were complete.
Item names as found in the source catalog, transliterated.
In SAP After enrichment
| Class | In SAP, % | After enrichment, % |
|---|---|---|
| All 44 classes | 57 | 86 |
| AC electric motors | 73 | 97 |
| Wiring accessories | 40 | 72 |
| Cable lugs and sleeves | 50 | 86 |
| Plug connectors | 61 | 89 |
| Insulating tubing | 59 | 86 |
| Insulating tape | 66 | 88 |
| Batteries | 64 | 94 |
01 · Enrichment
02 · Duplicates & analogs
| Match type | After enrichment | From SAP data |
|---|---|---|
| Duplicates | 24 | 9 |
| Likely duplicates | 159 | 54 |
| Analogs | 3,002 | 928 |
| Contradictions | 55 | 13 |
| Total | 3,240 | 1,004 |
03 · New records
| Already in the catalog | Materials |
|---|---|
| The same item | 2 |
| An active analog | 25 |
| An analog marked for deletion | 1 |
| No match — creation justified | 21 |
Client name withheld. Figures cover active items; SAP snapshot of 23 September 2026.
How we work
Contact
Tell us about your catalog or data platform. We’ll suggest where a pilot pays off first and what it takes to run it.