Aggregated Foot Traffic Datasets

Validate your next business decision with our machine learning-powered foot traffic datasets for the U.S.

Book a meeting
A 3d visualization of migration patterns map

Trusted by

BCG logo
Firefly Advertising logo
Carto logo
Esri logo
Google logo
Precisely logo
Spacewise logo
southern crown logo

Our Foot Traffic Datasets

Unacast provides foot traffic, trade area, cross visitation and demographic data to help you solve your biggest business problems.

A 3D visualization of foot traffic map

Understand visits in and around a location over time

Our foot traffic data helps you understand visitation at a specific site or area – how many people visit, types of visitors, and traits of the visit.

  • Number of people visiting a location
  • Time people spend at a location
  • Capture rate (how many people were in close proximity of your store vs. people who actually visited a store)
  • Customer loyalty (do customers return every month)
A 3D visualization of the Trade Area

Understand your key trade areas

Make better decisions by understanding the home and work locations of your visitors.

  • Areas where your visitors live and work
  • Distance your customers travel to your location
  • Gaps in store locations
  • Changes to your trade areas over time
Products Shopper Journey: A 3D map showing a shopper's journey through lines between businesses

Understand what other venues customers visit

Discover other shops and locations your customers visit.

  • Location cross visits
  • Patterns of visits
  • Changes to cross visits over time
A 3D visualization of demographics map

Understand visitor demographics

Determine what types of people are visiting a location.

  • Age
  • Education
  • Income level
  • Race
Our Methodology

How we build our aggregated foot traffic datasets

Our datasets are built with a privacy-first mindset to give you peace of mind as you solve your biggest business problems.
Step 1

Gather multiple data sources

Unlike typical aggregated products that rely solely on aggregating the underlying GPS device-level supply, our machine learning model is more robust and less dependent on GPS data fluctuations because it is based on a multitude of different data sources.

Our models begin with privacy-friendly first party location data. That data is then combined with contextual data including demographics, industry trends, venue attributes, historical data, and more.

Step 2

Build machine learning models

We train our machine learning models to learn the relationship between different data sources and our target mobility insights.

In total, the model comprises more than 120 features to train those relationships based on our long history of high-quality location data.

Step 3

Create curated datasets

Our machine learning-powered data is then curated into easy-to-work-with foot traffic datasets.

A common issue with using ML models is that they give you a prediction without any understanding of whether it is right or wrong. When validated against ground truth data, Unacast’s models recorded an R-squared value of up to .93, widely considered to be best-in-class.

Book a Meeting

Meet with us and put Unacast’s data to the test.
bird's eye view of the city