Skip to content

· via microsoft.com· Customer story

Properstar improves real estate search accuracy with AI-powered property filters

Properstar · Real Estate · Switzerland

Headline result

+98%

accuracy

As reported by the source; not independently verified.

Summary

Properstar, a Swiss-based international real estate platform, leveraged Microsoft Azure AI technologies to create dynamic, nuanced property search and filtering tools. Recognizing the challenge of incomplete, unstructured data from agencies and the limitations of conventional search filters, they partnered with Microsoft to rapidly innovate a more advanced platform.

Using Azure OpenAI, they extract and structure critical property details from millions of listings in multiple languages, expanding the searchable dataset by about 40 percent per property. Azure AI Search enables mandatory vs. optional feature settings for highly flexible, user-driven searches, ensuring buyers and renters do not miss relevant matches. The result is a platform achieving 98% property match accuracy.

Azure Synapse Analytics, Azure Databricks, and Power BI power market insights, perform big data-driven price analyses, and improve decision-making for users seeking the best value. Data collection, cleaning, and market reports are heavily automated, reducing manual tasks and increasing innovation velocity.

Security and compliance are managed with Microsoft Defender and standardized Azure protocols as Properstar scales globally, currently present in 65 countries. Future plans include AI-driven property concierge tools and voice/translation-enabled assistants to further enhance user experience. Properstar’s success demonstrates how data science and AI can transform online real estate discovery.

The problem

  1. 01Unstructured and incomplete property data from agency sources.
  2. 02Inefficient, rigid property filter systems that do not capture nuanced buyer needs.
  3. 03Unmet demand for accurate, flexible, and personalized real estate recommendations.

What they built

  1. 01Utilized Azure OpenAI to extract and structure key property information from diverse listings.
  2. 02Deployed Azure AI Search to enable granular property filtering (mandatory/optional features).
  3. 03Implemented Azure Synapse Analytics, Azure Databricks, and Power BI for advanced market analytics and reporting.
  4. 04Automated data pipeline with Azure DevOps and robust security with Microsoft Defender and Azure.

Reported results

  1. 01Increased property match accuracy to 98%.
  2. 02Expanded the information set by 40% per property for better search results.
  3. 03Enabled global platform scalability, operating in 65 countries with high security.
  4. 04Reduced manual workload and sped up innovation cycles with automation.
  • Built flexible AI property search filters
  • Improved market insights and price analysis
  • Scaled platform across 65 countries
  • Automated data processing and reporting

Source

microsoft.com

Customer story

Read the original(opens in a new tab)

How this deployment compares

Computed from the library · data 10 Nov 2026

Its reported 98% increase is above the typical range (median 40% across 51 figures).

Results against peers

98% increase is above the typical range

Across 51 quality & accuracy figures (all industries), the median increase is 40%; the middle half falls between 23% and 95%.

This recordMiddle half of peers

  • Revenue & growth67 figures, all industries · middle half 15%–150%40%median increase
  • Time & speed290 figures, all industries · middle half 30%–76%50%median reduction

Peer figures are as reported by their sources; percentage claims only.

How we checked this record

Evidence tier: verified

A primary source with a named customer and a supported deployment status.

Named organization
Properstar
Who published the source
The organization itself
Deployment status
Production (confidence 95%)
Quantified result
The source reports at least one figure
Summary checked against source
4 / 5 agreement

Last re-checked 13 Jun 2026.

This record is evidence for

Insight · patternProperty analyticsSee where this pattern is used and how it is built.

Same pattern, other organizations

All property analytics deployments
  1. 3 Jun 2026
    Real Estate

    Pointer automates real-estate property valuation and listing generation with Vertex AI (Cambodia)

    Pointer · Property analytics · GCP

    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.

    Production

    10×
    time
  2. Real Estate

    Leaseo streamlines property management with Google Cloud AI and Gemini

    Leaseo · Property analytics · GCP

    Leaseo replaced fragmented legacy property management systems with a single cloud-based AI platform to automate leasing, maintenance, inspections, and resident engagement workflows. Using Google Cloud AI services including Gemini models in Vertex AI, Leaseo deployed AI chatbots, call summarization, translation, video generation, and image analysis to enhance operational ease and customer experience. Google Kubernetes Engine and BigQuery underpin scalable, elastic infrastructure supporting AI-powered predictive and generative applications. Spaceman Consulting helped Leaseo migrate from AWS to Google Cloud, achieving 25% cost savings reinvested into AI-first strategy.

    Multi-agentProduction

    ↓ 100×
    cost
  3. Real Estate

    InvenTrust Properties Corp transformed real estate reporting

    InvenTrust Properties Corp · Property analytics · Microsoft

    InvenTrust Properties Corp, a leading multi-tenant retail real estate company, faced significant challenges in generating timely and accurate business insights needed for proactive leasing and property management decisions. Report preparation for monthly, quarterly, and annual financials often took up to three weeks, leaving little time for team members to conduct valuable data analysis or respond to ad hoc business requests. Slalom, the consulting partner, worked with InvenTrust to consolidate and standardize all company data, including financial actuals, CRM opportunities, budgets, forecasts, and demographic information, into a single SQL Server database hosted on Azure virtual machines. With the unified data platform, the team developed dozens of interactive Microsoft Power BI dashboards, giving business decision-makers on-demand access to critical property and business data. The dashboards allowed for visual, real-time analysis, enabling faster, more informed lease negotiations, forecasting, and property management decisions across InvenTrust’s 88 open-air shopping centers. The technology overhaul notably shortened the data compilation process from three weeks to just a few hours, freeing the accounting and leasing teams from manual reporting tasks and boosting their productivity. Business users, including leasing directors, now have access to mobile insights on-the-go, supporting rapid business decision-making in the field and direct competitive advantage in the leasing marketplace. Beyond providing reports, the transformation delivered hands-on Power BI training to employees, empowering them to create custom self-service dashboards as needed. This data strategy implementation positioned InvenTrust as an industry leader in leveraging data and analytics for commercial real estate management.