“Seeing is believing; Seeing is understanding; Seeing is discovering.”
In the world of business, one way in which “seeing” translates into reality is visualizing your data on a map. The insights thus derived from an additional dimension of ‘where’ can be very useful to spot patterns, that might be usually missed.
And, that is in effect what location intelligence is — when the most important parameter in all your analysis becomes “location” or “geography”.
Despite having a location component present in 80% of their data, organizations don’t leverage it to its maximum potential! Visit our previous article to explore the reasons for this gap and delve further into our story.
In this article, we have outlined some examples of how the most revolutionary companies have solved their business problems using a spatial lens.
According to this Forbes piece, the benefits of location intelligence isn’t just limited to the technical teams — R&D, sales and marketing verticals also benefit from it immensely.
Let’s examine how location is such an integral component across a broad spectrum of use- cases and complex features powered by advanced Machine Learning algorithms.
1. Uber: Geosurge Model
Booking an Uber cab seems such a simple and seamless experience. When you request for a cab in the app, it matches you with the closest available driver. However, there are intense algorithms running and tremendous data being crunched in the background.
Uber stores and monitor’s data for every trip- the distance traveled, the route taken, driver’s speed, acceleration, type of ride and cab etc. They also segment customers on parameters like app usage, ride patterns etc.
All of this data is fed into the geosurge model which determines dynamic surge pricing according to the availability of cabs (supply) and the frequency of ride requests (demand). This assures that the people who really need a ride can access it.
Diverse external factors such as a city’s transportation and movement patterns, weather, traffic, the time of the day, special events, neighborhoods etc. are also considered to predict the supply-demand, customers’ waiting time and even the driver incentives!
Using heatmaps ranging from light orange to red colors, drivers are recommended the areas to traverse to when they are waiting for rides.
It’s not common to see people getting agitated against these surge prices every now and then!
We have written about Uber's surge pricing in a lot of detail here:
2. Airbnb: Search Feature
“Our vision has always been to design the best possible experiences for users in places we haven’t been.” — Airbnb
Airbnb’s search has undergone several transformations in its quest to depict the most relevant listings for the user.
When the Airbnb Data Science team found out that the location of the listing mattered a lot to their users, they incorporated the location relevance component on top of the listing’s quality to yield the best results. The top listings showed up in areas where prior users ended up staying the most.
They also envisioned this location element to aid users in discovering the entire city — including the culturally rich regions (sometimes, not even drawn precisely on maps) and not just the traditional travel hotspots!
To increase the likelihood of bookings, the prices are tweaked not only based on the locations of the listing but also on user’s location. Location-specific insights like availability of rooms, community events etc are showcased as well to improve customer experience in its entirety and enable informed decision making.
Location Intelligence has swept borders of tech companies to make an impact in the traditional brick and mortar businesses as well! After all, the location and visibility play a key role to attract customers.
Check out the applications of location data by Airbnb:
3. Starbucks: Site Planning
Starbucks tapped into the power of location data to do a suitability analysis by comparing potential locations and pinpointing the most suitable one for expansion.
Some of their preference criteria included (a) in neighborhoods of $60,000 and over median household income; (b) having an employee base (c ) adjacent to national and regional retail tenants (d) around traffic counts of at least 30,000 vehicles per day on surrounding streets; (e) at signalized corners and having multiple access points;
The Starbucks team started by mapping their existing set of cafes and their operations network. Further, they performed an in-depth segmentation of their customers on the basis of demographics, frequency of visits and movement patterns.
On top of current stores data, they layered troves of external data such as demographics, household income, employment, competitor presence, traffic, points of interest such as markets, transportation infrastructure etc. to select the most optimum location.
This exercise also helped them relocate some stores with low footfall into these “high prospects” — capturing market share from their competitors.
Read more about how Starbucks uses geospatial analytics to plan their next set of stores:
4. Walmart and Burger King: Geotargeting
Location data has become a widespread tool for marketers. It is exceptional in depicting where all have the customers frequented, where they currently are and also where they are most poised to visit again.
It is thus an effective way to reach out to them in a specific area at a given time, maximizing the return on investment.
Location patterns have the ability to sketch out people’s journeys, habits, behavior and psychological traits. Giants like Walmart and Burger King have used these patterns to increase the footfall in their stores and restaurants.
Walmart used location-based audience targeting according to the logic “people belonging to a particular neighborhood, on an average, behave in a particular way.”
Burger King ran a promotional campaign where they offered anyone near a McDonald’s a $1 burger in any of its nearby branches. This kind of marketing is called proximity targeting.
Explore more uses by food delivery companies in location analytics:
5. Mastercard: Fraud Mitigation
Mastercard has started using their customers’ location to protect payments and combating fraud.
The users can only make a transaction when their mobile device is switched on! Mastercard facilitates a more secure payment environment by matching the location of the phone and the card being used.
This feature enhances customer experience manifold — especially by avoiding automatic blocking of the card while when traveling abroad. This system worked globally and without the need for any additional infrastructure!
The team also undertook a location-based analysis exercise to identify spatial patterns in fraud and implement policies accordingly.
However, they lost billions of dollars in sales due to false declines — more than 13 times the total amount lost to actual card fraud! In response to this, they developed a decision intelligence model which gives a predictive score to each user for every transaction based on factors such as account usage over time, their location, purchases etc to check for any anomalies in their behaviour.
This increases the accuracy of genuine approvals and authorization decisions during payments, without compromising on risk.
“We are solving a major consumer pain point of being falsely declined when trying to make a purchase,” — Ajay Bhalla, president of enterprise risk and security, Mastercard.
6. Insurance: Risk Assessment
Insurance companies such as Amica, Aon and Zurich use spatial analysis to prune their exposure to risk.
When a disaster strikes, it is imperative for these folks to be informed with real-time mapping to act quickly. They do this by examining the policyholders who are most adversely affected and the authenticity of their claims with respect to the damages caused.
This also assists the insurers to investigate all the outlier requests for fraudulent cases — so that they can allocate their resources and improve outreach for the victims in dire need for the claims.
The insurers have developed a system to rapidly deploy location-specific communications and services for all communities in the projected path of a disaster. When provided with updated maps of disasters, the field adjusters also help people struck evacuate or spot emergency services.
These companies also engage in location-based bias-free pricing for their customers. The prices are based on factors like the probability of disaster hitting the areas, historical costs, claims, expenses. Fair pricing practices also lock-in customers and maximize their lifetime value.