Geometry data

Access Accurate Building Footprint Polygon Data with SafeGraph

Reduce attribution errors with high-quality building footprint data. Incredibly accurate POI footprint data offers a clear picture on the boundary of a place, so you can perform the most accurate analysis.

Hone in on location accuracy with precise polygon data

Our Geometry attributes help data leaders to better understand the shapes of points of interest (POIs) and their relationships with other places.

Access robust polygon geometry data that includes:
The shape of the place as Well-Known Text (WKT)
Spatial hierarchy metadata showing relationships between polygons
Additional attributes related to parking lots and polygon quality

Explore notable polygon data rows

Parking Lots

A premium set of Geometry rows depicting the shape and size of surface parking lots and their relationship to surrounding POIs.

High Quality

Maintaining your own database of polygons is challenging

You need data you can trust and rely on. We apply complex engineering and human verification to ensure accuracy of all POIs in our datasets.

Learn more about SafeGraph Geometry
Example of accurate polygon building footprint
Polygon data is complex to create and maintain. SafeGraph Geometry data provides reliable and accurate building footprints verified by actual people, so you can be confident in their veracity.

Inaccurate data is costing you time and money

Our accurate polygons allow you to reduce errors and more precisely attribute consumer visits to a specific place. Human verified building footprints are far superior to using a centroid radius, allowing you to determine who actually enters a POI versus who simply walks nearby.

Read our guide to visit attribution
Example of why a polygon is more accurate and better for analysis than an isochrone
Building footprints are the only true representations of place boundaries; a centroid radius or an isochrone is not granular enough for precision analytics.

Our world is complex - we make analyzing it easy

We give you metadata so you can easily distinguish the spatial hierarchy and relationship between different places. With clear polygon hierarchies that have parent-child relationships, you’ll gain detailed insights about the POIs you’re analyzing.

Explore the data schema
Spatial hierarchy metadata provides important information about POIs
Spatial hierarchy metadata reveals how places relate to each other, such as a store within a shopping mall or a suite within an office complex.

Download a free sample of Geometry Data

Explore precision polygons for global places.

Geometry Technical Docs
Want to know more about the datasets themselves? The following resources are available to access at any time.
1. Geometry data schema
Learn the schema for the Geometry dataset so you understand all attributes in the metadata.
2. Release notes
Get access to the latest product release notes so you always have the most current information about the datasets you’re using.
3. Summary statistics
Get a quick overview of what’s relevant in the datasets you’ll be using, and what data is available for you to access.


Get your data easily in any of the following 3 ways:
1. Bulk download
Configure an S3 bucket for monthly data deliveries
2. Snowflake
Query and download SafeGraph Geometry directly through Snowflake to easily integrate our data into your workflows.
3. Request a sample
Reach out and try SafeGraph Geometry for yourself. Explore the columns included and see the possibilities for enriching your current data.


What is polygon data & what does it include in Geometry?

A polygon is a GIS feature that encloses a geographical object to represent a physical boundary in the real-world. A polygon, or building footprint, provides a two-dimensional representation of a real-world location on a map, such as a park, building, parking lot, or pretty much anything with a defined perimeter.

These polygons - especially when paired with other consumer behavior information like mobility and spending data - offer clear insights into a building’s footprint, which can be used to identify foot traffic at a location, clearly define a catchment area, and much more.

How much does the Geometry dataset cost?

Like all of our data, the cost of Geometry depends on the amount of rows, columns, and frequency of delivery you request. Contact our sales team to learn about enterprise pricing.

How often is the dataset updated?

SafeGraph issues updates to Geometry once per month, which is much more frequently than other POI vendors, who may update once every 3-6 months. We can do this because we work with more sources of data and are much more efficient at combining those sources. During each month, some subset of our sources will send us their updates, and we ensure that we onboard and integrate those changes quickly and easily.

This enables us to quickly reflect store openings and closings in our POI database. The time between a store opening/closing and being reflected in our POI database is approximately equal to the time that the store update is seen by one of our sources and the time it takes SafeGraph to reflect this in our data. The latter of these two is typically within the month, which is very fast compared to other providers, which might be within 3 months. The former of these two is hard to predict - but we do work with sources that generally receive updates very quickly.

How do you determine spatial hierarchy or overlapping polygons?

We identify spatial relationships (what we refer to as “spatial hierarchy”) by measuring polygon overlap. For each pair of overlapping polygons, if the larger polygon contains at least 80% of the smaller polygon, and if the larger polygon is also of a particular POI category, then we mark it as the “parent” of the smaller polygon. It’s important to restrict parent POI candidates to a specific set of categories or brands so that we’re not solely reliant on polygon precision to determine spatial hierarchy. For example, we want airports to be parents when overlapping other POIs, but we generally don’t want cafes to be parents if overlap exists and the cafe happens to be the larger of the two polygons. See our Geometry docs for a complete list of POI categories that are eligible parents. We flag these relationships in our geometry data by setting the “parent_placekey” of the smaller POI equal to the “placekey” of the larger, encompassing POI. We colloquially refer to the larger, containing POI as the "parent" and the smaller POI as the "child."

How do you deal with POIs that are completely enclosed by others?

Similar to determining eligible parent POIs, we rely on categories to distinguish enclosing vs. non-enclosing spatial hierarchy relationships. See our Geometry docs for a complete breakdown of the spatial hierarchy relationships we treat as “enclosing.”

Although simple, the enclosed column is super important fuel for our visits algorithm. Due to GPS drift within major structures, when 'enclosed' = “true,” we exclude visits to that POI and only attribute visits to the parent POI. We pride ourselves in archiving facts, so we would rather not attribute visits at all than make rash assumptions.


Learn more about accurate and precise global POI data