Top-10 e-commerce platform, IndiaLive

Pricing millions of SKUs without the catalogue leaving

A self-hosted pricing engine benchmarks the whole catalogue and recommends SKU-level changes. Sales lift remains a target, not a measured result.

Delivered by our founding team at a previous firm. Clients anonymised under NDA.

In brief

What problem needed solving?

Pricing millions of SKUs, without leaking the catalogue. Routing proprietary catalogue and margin data through a hosted multi-tenant model was not acceptable; sampling misses the long tail where margin leaks.

What did the team build?

A purpose-built, self-hosted pricing and coverage engine trained on the catalogue, running inside the platform's own environment. It benchmarks every SKU, surfaces pricing moves at catalogue scale and gives SKU-level recommendations on a live dashboard. A small role-specific model, owned, not a rented generalist.

What changed?

Pricing and coverage benchmarking now runs across the whole catalogue, not a sample, with the catalogue and margins never leaving the perimeter. The engagement is measured against a targeted 15% sales lift at SKU level. A small owned model runs inside the perimeter instead of a hosted generalist model.

Deployment and target

targeted 15%
sales lift at SKU level
target

Delivered by our founding team at a previous firm. Clients anonymised under NDA.

Catalogue in. Pricing guidance out. All inside the perimeter.

  1. Catalogue & margins

    Proprietary data stays inside.

  2. Private pricing model

    Benchmarks every SKU, not a sample.

  3. Pricing guidance

    SKU-level recommendations on a dashboard.

Live. Delivered by our founding team at a previous firm. Clients anonymised under NDA.

Bring one problem.

Tell us about one costly process. A founder replies within two working days.

Start with the problem. Agree the right next step together.

For example:

  • a document your team retypes
  • a queue that grows with volume
  • data that can't leave the building