Independent

Omorfia GIS - Right-sizing a 134-branch UAE salon network

An 8-brand, 134-branch UAE salon group needed objective evidence about which branches to retain, consolidate, or relocate, and where to expand. Existing decisions were anecdotal; financial signals alone missed location dynamics.

2025

Approach

Built a geospatial decision platform ingesting Google Maps signals, TravelTime drive-time isochrones, WorldPop demographics, and internal financials. Designed a composite risk model to classify branches and an H3 hex-grid tessellation of the UAE for expansion zones. Delivered as a React + MapLibre + Cesium dashboard and a FastAPI backend exposed through ChatGPT Actions and an MCP server integrated with Claude.

Architecture sketch

The platform is split into three planes:

  1. Data plane - nightly batch ingestion of Google Maps signals, TravelTime isochrones, and WorldPop demographics into PostGIS, joined to internal financials.
  2. Analytics plane - composite risk scoring and H3 tessellation; PostGIS spatial joins for trade-area analysis.
  3. Experience plane - React + MapLibre/Cesium dashboard for analysts; ChatGPT Actions + MCP server for natural-language strategic questions.