Intelligent Search · Advertising · production
MediaX
Semantic and geospatial OOH recommendation engine.
LLM-driven system that transforms natural-language campaign requirements into structured geographic intent, retrieves inventory, and ranks placements across 290+ UAE categories in under five seconds.
Problem
OOH campaign planning requires translating vague location language into validated geo-i…
System
An intent parser plus geospatial retrieval and weighted ranking pipeline with enrichmen…
Role
Applied AI / Search Systems
Status
production
Outcome
290+ UAE POI categories
My role
Applied AI / Search Systems
- AI Architecture
- Retrieval
- Backend Engineering
- Data Pipelines
- Productionization
Period / 2025
Geospatial OOH media discovery
INTENT
Plays once · tap to replay
Problem
OOH campaign planning requires translating vague location language into validated geo-intent and ranking inventory against footfall, traffic, POI density, and proximity—manually and inconsistently.
System
An intent parser plus geospatial retrieval and weighted ranking pipeline with enrichment, caching, retries, and idempotent upserts for reliable recommendation responses.
Architecture
Natural-language campaigns flow through intent parsing, geo/POI resolution, semantic validation, geospatial retrieval, and a weighted ranking engine into inventory recommendations.
- NL Campaign → Intent Parser
- Intent Parser → Geo + POI Resolution
- Geo + POI Resolution → Semantic Validation
- Semantic Validation → Geospatial Retrieval
- Geospatial Retrieval → Ranking Engine
- Ranking Engine → Inventory Recommendation
Execution path plays once on view · hover a node or tap the canvas to replay
System anatomy
Architecture
Intent → geo resolution → retrieval → weighted ranking.
- Intent parser
- Geo/POI resolution
- Ranking engine
- API enrichment
Engineering decisions
Decision
Structured geo-intent extraction
Constraint
Campaign language is ambiguous and uneven across advertisers.
Approach
Parsing into validated locations and POI types makes retrieval deterministic and auditable.
Result
Deterministic geo-intent for inventory retrieval.
Decision
Weighted business ranking
Constraint
Inventory quality is multi-signal — not a single model score.
Approach
Explicit weights (30/30/20/20) encode business priorities instead of opaque model scores alone.
Result
Auditable ranking across footfall, traffic, POI density, and proximity.
Decision
Caching, retry/backoff, idempotent upserts
Constraint
External APIs and enrichment steps fail under load.
Approach
Retry/backoff, caching, conflict resolution, and idempotent writes keep the pipeline production-safe under load.
Result
Production-safe enrichment under external API volatility.
Reliability
- Retry / backoffACTIVE
- CachingACTIVE
- Conflict resolutionACTIVE
- Idempotent upsertsACTIVE
- Location semantic validationACTIVE
Outcome / Results
- Natural-language campaigns mapped to structured geo-intent and POI types.
- Weighted ranking across footfall, traffic, POI density, and proximity.
- Optimized recommendations returned in under five seconds.
Stack
Product visuals
