Spatialzr developed Spatialzr LISA, the first forward-looking attractiveness scoring system for commercial real estate assets, comparable like-for-like across all geographies.
LISA answers the question that standard market data doesn't ask: what is the attractiveness trajectory of this exact cell over the next 3 to 5 years — before the market turns?
In two years, Spatialzr has designed, tested and consolidated a standard location score for commercial real estate:
2023: Exploration of needs in the real estate scoring market and architecture of the first public‑data aggregation model.
2024 / 2025:
We follow a continuous improvement approach: every POC, every dataset and every regulatory change feeds into the value of our score.
In commercial real estate, most models start with financial metrics. Spatialzr does the opposite: we start from location intelligence as the fundamental layer – spatial data, accessibility, points of interest, urban and environmental context – and then stack building, asset and market data on top. This is what makes the LISA score a true location standard, not just a bolt‑on to traditional valuation models.
Research such as McKinsey’s shows that nearly 60% of a real estate model’s predictive power can come from location and neighbourhood characteristics, far beyond rents or yields alone. Spatialzr responds to this by offering a location score specifically designed for commercial real estate (CRE), turning complex open data into a reliable indicator to assess a site’s potential – across office, retail, logistics or residential use cases.
Whether you are an investor, broker, developer, valuer or asset manager, LISA becomes a shared column that helps you compare sites, analyse portfolios and select the best locations in a location‑first mindset
Source (insight on location-related predictive power): McKinsey & Company, “Getting ahead of the market: How big data is transforming real estate”, 2018.
Real estate assets are fixed and long‑term: location is therefore key. At Spatialzr, we believe reference data should be built on public spatial data – scalable, structured and universal. On this basis, LISA is designed as a standard reference layer for real estate decisions.
Our methodology evaluates each site across six weighted factors:
📍 Metropolitan area
🚉 Transport accessibility
🛍️ Retail activity
🏢 Business density
🌆 City life
🌿 Environmental factors
The resulting score can be adjusted to reflect best use – office, retail, logistics, residential – or kept as a standard score for general assessment. It can be enriched with complementary data (transactions, footfall, ESG, turnover, etc.) or tailored to a specific investment strategy.
Spatialzr designs LISA as a standard location building block, meant to plug into existing models rather than replace them. While many solutions remain black boxes or closed interfaces, LISA delivers a transparent score, based on structured public data, that you can use as a reference column inside your own models.
Spatialzr is led by Cyril Théret, with more than 20 years of experience building marketplace platforms and data solutions for real estate and finance in France and the United Kingdom. This dual market‑and‑data background fuels the design of LISA as a location standard that investment, asset management and risk teams can use directly in their models.
![[object Object]](https://umsousercontent.com/lib_AzpNsgWyClRyCwLd/j5tmqaiaxn1kdzz9.png?w=234)