04·AI / ML
Atlas
Entity-centric real-estate valuation platform. Confidence-tiered ontology, hex-grid geospatial risk modelling (flood, vegetation, urban classification), six-month price forecasts. Pulls from RTA, KHDA, EIBOR, World Bank, and Airbnb open datasets.
What it took
The skills behind this project.
Every project below leans on a primary discipline and a handful of secondary ones. Tap any chip to see how that skill plays out across the wider portfolio.
Skills demonstrated
- Backend EngineeringPrimary
FastAPI service on PostgreSQL with a hex-grid spatial index and confidence-tiered entity ontology.
- AI & Machine LearningSecondary
Six-month price forecasts and geospatial risk models (flood, vegetation, urban classification).
- Data PipelinesSecondary
RTA, KHDA, EIBOR, World Bank, and Airbnb feeds reconciled into one analyst surface.
- Frontend EngineeringSecondary
React + Cesium brief view that turns multi-day analyst cycles into on-demand ranked opportunities.
Context
Why it exists.
BARNES Dubai's valuation team was running multi-day analyst cycles to produce ranked opportunity briefs — pull RTA transactions, cross with KHDA, eyeball portal scrapes, layer in flood and vegetation risk. Each brief was excellent and was finished a week after the listing moved.
Atlas collapses that cycle into an on-demand surface. An entity-centric platform: every property, every transaction, every neighbourhood, every owner is a first-class entity with a confidence-tiered ontology. The valuation team queries it the same way they think — entities, relationships, tiers — and the brief comes back in seconds rather than days.
The hard part is not the FastAPI service; it is the reconciliation. RTA, KHDA, EIBOR, World Bank, and Airbnb open data do not agree on what a building is called, how a unit is referenced, or which currency a price is in. Atlas's job is to make them agree without lying.
StackPython · FastAPI · PostgreSQL · Cesium · React · Machine-learning pipelines
Process
The decisions that shaped it.
- 01
Confidence tiers everywhere, not just on prices
Every entity carries a confidence tier — high for direct RTA transaction records, lower for inferred matches across portals, lowest for derived calculations. The brief surfaces these tiers explicitly: an analyst should be able to tell, at a glance, which numbers came from the registry and which were inferred. Hides nothing, claims nothing it cannot back.
AI & Machine Learning - 02
Hex-grid geospatial risk, not polygon overlays
Flood, vegetation, urban classification, and walkability were modelled on a hex grid rather than on irregular polygons. Hex cells aggregate faster, query consistently, and visualise cleanly at multiple zoom levels. The same hex layer renders in Cesium for the analyst surface and powers the six-month forecast pipeline downstream.
Data Pipelines - 03
Six-month forecasts conditioned on local supply
Forecasts are not free-floating extrapolations; each is conditioned on local supply (off-plan launches, completion timetables) and macroeconomic anchors (EIBOR, World Bank). The model surfaces both the prediction and the contributing factors, so the analyst can challenge the forecast on the factor that looks wrong.
AI & Machine Learning - 04
Brief view that reads like an analyst memo
Built the React + Cesium surface to read like the memo the analyst would have produced manually — narrative paragraphs, ranked opportunity list, map, supporting tables. The platform's job is to draft the memo; the analyst edits and signs. No dashboards full of widgets nobody clicks.
Frontend Engineering
Outcome
What shipped.
Turns multi-day analyst cycles into on-demand briefs and ranked opportunities for the BARNES Dubai valuation team.
In production with the BARNES Dubai valuation team. Multi-day analyst cycles are now on-demand briefs; the analyst spends time on the harder cases instead of repeating the same lookup five times an hour. The data pipeline backbone is also the source for the Barnes AI multi-agent research system.