Methods blog · AI Foundations & Applied AI
LandSinLandSin: privacy-preserving land-value estimation and habitability insights on the web
A web application that pairs polynomial regression with differential privacy to estimate land values from local amenities, and adds affordability, habitability and terrain insights through Google Maps.
#web server#differential privacy#regression#urban planning#Google Maps API
Land-value estimates drive investment, taxation and regional planning, yet they are often opaque, slow to produce and built on sensitive transaction data. LandSin, published in Software Impacts and developed in the lab with collaborators, is a web application with a back-end database that makes land-value estimation fast, explainable and privacy-preserving.
Ingredients
- Polynomial regression on property details and local amenities, capturing non-linear effects (a generic polynomial model is shown below):
- Differential privacy (DP) to protect contributors’ data. A DP mechanism adds calibrated noise so that the released outputs reveal almost nothing about any single record. Formally, a mechanism \(M\) is \(\varepsilon\)-differentially private if, for neighbouring datasets \(D, D'\) and any output set \(S\), \(\Pr[M(D)\in S] \le e^{\varepsilon}\Pr[M(D')\in S]\).
- Google Maps integration for terrain context and location-aware features.
Features
- Land value and price prediction for a chosen location.
- Affordability and habitability analysis.
- Terrain insights from Google Maps.
- Infographics that highlight economically deprived but habitable areas.
Who it is for
- Real-estate agencies and investors: assess opportunities and market trends with data-driven estimates.
- Community planners and governments: identify economically deprived yet habitable areas to target balanced regional development.
- Individuals: obtain informed estimates without exposing private data.
LandSin shows how standard statistical models, combined with modern privacy guarantees and good interface design, can become decision-support tools for the public sector, a direction the lab is pursuing with grants on public-sector analytics.
Read the paper
-
LandSin: A differential ML and Google API-enabled web server for real-time land insights and beyond
Software Impacts 22, 100718 · 2024