Our Data
Validate your next business decision with our machine learning-powered human mobility insights.
Validate your next business decision with our machine learning-powered human mobility insights.
Our datasets can help you understand migration trends in the U.S., foot traffic to your locations of interest, and the origins and cross visits of your visitors. With machine-learning powered insights, you can make more informed decisions for site selection or deselection, boost your competitive advantage, and so much more.
Learn where, when, and which kinds of customers visit your competitors’ locations instead of yours (and vice versa).
Measure the impact of increased staff engagement, new products, pricing, and advertising.
Identify gaps in the local marketplace and other opportunities to expand your portfolio.
Understand how individual stores within a given brand are performing to selectively close or promote them.
Determine which community characteristics and population demographics help create a lasting visitor base.
Analyze population movements and the impact they have on local communities.
We provide foot traffic, trade areas, cross visitation, and migration pattern data to help you solve your biggest business problems.
Our Foot Traffic Dataset helps you understand the visitation at a specific site or area – how many people visit, types of visitors, and traits of the visit (when they visit, how long they stay, and how often they return).
Make better decisions by understanding home and work locations of your visitors.
Identify what shops your customers also visit to learn about their shopping preferences.
We gather data sources like GPS location data (from 130M+ smartphones and mobile apps), weather, demographics, industry trends, venue attributes, historical data, and more.
After cleaning, correcting, and preprocessing, these data sources serve as features we feed into our industry unique machine learning model.
Using multiple data sources allows us to build a more robust and reliable understanding of mobility that is less dependent on GPS data fluctuations and quality because it is based on a magnitude of different context.
Read More
From the multiple data sources, we create a feature library that allows us to build our machine learning models that find relationships between different data sources and our target mobility insights.
Each machine learning algorithm is selected and we train our models on a training dataset to optimize its performance. Thereafter the trained model is evaluated on a validation set for its performance. We address any issues and improvements to the model before putting it in production. Once deployed in production, it runs on new data as it becomes available to calculate mobility insights.
Read More
We have datasets depending on your data maturity and needs: Foot Traffic, Dynamic Trade Areas, Cross Visitation, and Migration Patterns.
A common issue using ML models is that those always give you a prediction without understanding if that is right or wrong. When validated against ground truth data, Unacast’s models recorded an R-Squared of 91.6% or higher, widely considered to be best-in-class.
Read More
