Normalized claim
Accuracy: 30% increase
Valuation accuracy increased by 30%.
Pointer automates real-estate property valuation and listing generation with Vertex AI (Cambodia)
Use case typeProperty analyticsUpdated Jun 13, 2026
Pointer is a tech-enabled real estate agency in Cambodia that is building a platform to professionalize the local property market with accurate, transparent valuations. To support that goal, Pointer migrated its infrastructure to Google Cloud and built an end-to-end data platform centered on Vertex AI, which automates ingestion, cleaning, training, testing, and deployment of its price prediction models. Vertex AI also generates property descriptions from uploaded images for the AgentHub app, while Looker dashboards provide market insights and Google Maps Platform adds geospatial context for listings and user interaction.
- Organization
- Pointer
- Industry
- Real Estate
- Location
- Cambodia
- Published
- June 2026
Reported outcomes
10x
timeTime & speed
+30%accuracy15 minutestime5 minutestime−75%quantified impact
Strategic outcomes
New product / capabilityAutomated property description generationSpeed & agilityAccelerated model update cyclesSpeed & agilityFaster property listing creationBetter decisions & insightFaster market insight delivery
Catalog median for time & speed deployments: +60% across 143 reported metrics. Compare benchmarks →
Why do we believe this?Outcome claims, sources, and evidence checks
Normalized claim
Time: 15 minutes decrease
Property listing time dropped from 15 minutes to 5 minutes.
Normalized claim
Time: 5 minutes decrease
Property listing time dropped from 15 minutes to 5 minutes.
Normalized claim
Quantified impact: 75% decrease
The AI team’s workload was reduced by 75%, with work that required four data scientists now managed by one.
Normalized claim
Time: 10 x increase
Looker delivered business insights 10x faster.
Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
- Customer
- Pointer
- Provider
- GCP
- Maturity
- Production
- Linked source
- Google Cloud Customer Stories
Used Looker dashboards for market-trend and operational insights, and Google Maps Platform for geospatial context
Customer identity supportedSource describes one deploymentMaturity supported
Primary read
Use case focus
Showing 3 of 3
- 1Property valuation automation
- 2Listing generation automation
- 3Predictive analytics
- Manual data cleaning and model training slowed AI development.
- Weekly model updates required nearly a month.
- Creating property listings in the AgentHub app took about 15 minutes.
- Pointer needed accurate, transparent property valuations for agent licensing and accountability.
- Migrated infrastructure to Google Cloud with partner Tridorianto.
- Built an end-to-end data platform to power internal analytics and the AgentHub app.
- Used Vertex AI as the core engine for the machine learning pipeline to ingest, clean, train, test, and deploy price prediction models.
- Configured Vertex AI to generate property descriptions from uploaded property images.
- Used Looker dashboards for market-trend and operational insights, and Google Maps Platform for geospatial context.
Technologies
- Valuation accuracy increased by 30%.
- Property listing time dropped from 15 minutes to 5 minutes.
- The AI team’s workload was reduced by 75%, with work that required four data scientists now managed by one.
- Model update cycles fell from nearly a month to a week.
- Looker delivered business insights 10x faster.
Architecture
Pointer migrated to Google Cloud and built a centralized data platform around Vertex AI. The platform automates the full ML workflow—data ingestion, cleaning, training, testing, and deployment—for property price prediction models. Vertex AI also generates listing descriptions from property images, Looker supports analytics and market-trend reporting, and Google Maps Platform supplies map-based context in the app.
Sources & evidence1
Evidence: Medium65/100Evidence strength
- Customer explicitly identified
- Deployment status explicitly supported
- Primary source available
- Quantified outcome available
- Technical implementation details available
Type: Customer StoryPublished: Jun 3, 2026Publisher: Google CloudEvidence: VendorConfidence: High
AI-generated summary. Verify important details with the linked sources before relying on this case.
Explore related AI use cases
Customer evidence
Provider evidence
Browse the catalog
Was this useful?
Community
Comments
No published comments yet.