Spatial analytics harnesses real world location information and artificial intelligence to power a wide range of business use cases.
A discussion of spatial analytics must begin with a quick definition of what spatial data (sometimes called location data) is.
As physical location can be gathered via IP address from a landline, spatial data in the form of GPS signals is gathered from common mobile devices. This includes mobile phones, beacons, Wi Fi, raster data (think: satellite images), connected vehicles, and other remote sensing devices that keep track of where people and things are.
Once gathered and processed, this data can be studied through spatial analytics tools and methods using readily available open source and commercial data sets. Several such options exist, the most powerful being secure platforms crafted for large, first party data owners, such as telecommunications companies.
Telcos are really the gold standard stewards of first party data. They have the greatest volume of data and it is rich in both the temporal and spatial sense. Telco is arguably the most privacy-friendly industry to begin with also, by design.
But rather than diving into the technical weeds, let's look at how spatial analytics are used in real world use cases by a range of industries, and for a variety of reasons.
Within about two months of the start of Covid, we didn't need to rely on anecdotal evidence of urban exodus anymore -- it was in the data. Whole urban centers went dark, while smaller areas lit up for an increase in activity.
At the same time that Florida's southeast and the Miami area were going boom, San Francisco and the Bay Area went bust. Houston got hammered, but its surrounding counties built-up. All of this population movement carried serious economic consequences -- billions left cities and settled in suburbs or towns, reshuffling the economic landscape of America.
This created new foot traffic patterns in growing communities with evolving needs for public services and spaces. The human reshuffling also meant retailers and restaurateurs were flush with options for store location, reshuffling site selection processes for many real estate investment teams.
This brings us to another common use case for spatial analytics: using different types of location data to inform decision making around different types of investments.
From global banks using migration patterns data to increase return on assets, to insurers using location data to optimize profitability, spatial analytics inform investment decision making every day.
Location data from GPS signals can be used in the rearview mirror - as in validating real estate investments - or to look ahead to what may be, as in predicting quarterly revenue based on current foot traffic patterns.
Location intelligence and spatial analytics can also be augmented with other data streams to inform investment and business strategies of all types, including how to beat the competition.
Just like you can use geospatial data and analytics to understand your own business, you can also use it to improve what you know about the competition. This is of particular importance for enterprise retailers, restaurateurs, grocers, coffee shops and big box stores.
From a high level, KFC looks like it's whooping chicken butt most everywhere north of Louisiana. But zoom in with a spatial analytics visualization tool and you'll see Popeyes is fiercely competitive in major urban markets across the map.
Target is the dominant big box nationally, but Costco has pockets of strength. Location data run through some geospatial analytics tells us that breaking through the Rockies would go a long way to solidifying Costco’s regional presence.
Kroger and Publix fight for much of the Great Lakes region and Atlantic seaboard but it is the urban markets of Georgia where the decisive battle may happen in 2023. All of this competitive intelligence was derived using raw foot traffic data and simple spatial analytics tools to study the relative mobility patterns of each brand's visitors.
This agility of application is why so many new products are being built from geospatial data resources.
While latitudes and longitudes are the only raw ingredients, the products that can be cooked-up through spatial analytics are endless. One of the more interesting use cases in early 2023 is how location data is being applied to create new products in the parametric insurance industry.
The traditional insurance industry relies on a manual claim event to trigger the payment process. One day, when the red tape has been hacked through, you hopefully get some kind of payout. But that reactive approach is not a formula that works in the wake of a natural disaster.
Enter parametric insurance: quick, automatic payouts based on fixed thresholds, like the size of hailstones, or the wind speed of a hurricane. When the threshold is met, payment is triggered. The worse the event, the bigger the payout.
An interesting 2023 evolution: insurers are preparing new products for businesses that lose foot traffic temporarily or permanently because of a natural disaster. It’s a fascinating technical and business disruption at the right moment in time, and it's a good use of secure data.
At Unacast, we are committed to protecting and respecting data privacy and see privacy as a key driver for the growth of location technologies. Our privacy program covers the flow of location data from the point of collecting location data to our customers’ platforms.
If you'd like to learn more about spatial analytics, please contact us today.