One source of truth for a multi-brand retailer
Client: Northgate Retail Group
- 10x
- faster month-end reporting
- 11
- systems unified into one platform
- 99.9%
- pipeline reliability
The challenge
Five brands, eleven systems, and no shared definition of revenue. Month-end reporting took two weeks of manual reconciliation, and leadership had stopped trusting the dashboards.
What we built
We consolidated their estate into a governed lakehouse — dbt-modeled, contract-tested, with a semantic layer feeding every dashboard from one set of definitions.
How we did it
- 01
Two-week data audit across all eleven systems, producing a prioritized map of sources, quality issues, and conflicting metric definitions.
- 02
Negotiated one shared definition of revenue, margin, and inventory with finance and merchandising before writing any pipelines — the political work that makes the technical work stick.
- 03
Built contract-tested ELT into a governed lakehouse, with dbt models and data lineage so every number is traceable to its source.
- 04
Shipped a semantic layer feeding every dashboard from one set of definitions — killing the eleven competing versions of the truth.
- 05
Left behind runbooks, alerting, and a trained internal team; the platform runs without us.
The result
Month-end closes in two days instead of two weeks, and every team from merchandising to finance reads from the same numbers.
Stack
Services used
- Data Engineering
- Cloud & DevOps
More work