Behavioral Data – The Unfair Advantage in the Digital Era

The emergence of advanced tracking and sensory technologies, as well as solutions that focus on gathering behavioral information online represent a source of unimaginable value for businesses dealing with the consequences of consumer delinquency or any other human-related risk. Forbes emphasizes that telematics or wireless communication of data back to an organization and AI can take predictive abilities and customized products to the next level by recognizing GPS patterns with the data, inferring road & traffic conditions, and even predicting and helping avoid accidents, which could potentially lead to fewer claims to process as well as safer and more satisfied customers.

Financial services and insurance industries are the ones most dependent on the ability to understand and build predictive models of human behavior. The opportunity for those industries has two sides – the ability to anticipate defaults, and fraud prevention. In fact, when making lending decisions, analyzing behavioral information in addition to financial information can help a lender avoid a loss of about 5.58% on a quarter of its portfolio, according to Moody’s Analytics. A case study by BioCatch based on work with a global credit card issuer revealed that adding behavioral biometrics technology into online application workflow to act as another dimension in separating out legitimate users from fraudsters led to 50% more accurate fraud alerts than existing solutions, 33% less false declines, and 100% alerts either being confirmed as fraud or highly suspicious.

There is another very interesting example of how user behavior can be read and analyzed by a machine and other humans, described by BioCatch. The solution was able to prevent a false positive for fraud, while internal systems of a credit card issuer calculated a 96% chance of the application being fraud. Positive signs that behavioral system read as indicators of a genuine application were described as following:

  1. The use of long-term memory as seen by typing, with no pause, a nine-digit SSN (fraudsters cannot type nine digits in one go as short-term memory is limited to up to seven digits; so, when they type a victim’s SSN they would normally pause after a few digits, take another look at their record, and then complete the typing).\

  2. This was an application for a hotel chain credit card, and the hotel’s loyalty number was requested. Fraudsters normally come prepared an immediately provide the information, but users normally don’t and have to look for the number as it’s not top-of-mind. In this session, there was a 58-second pause while the user was fetching the data.

The use of behavioral data represents a conceptual shift – from static to dynamic approach in assessing the environment in which the business is conducted and how its main agents act in that environment. The results of a continuous, dynamic assessment with translates into the ability to push the right information at the right time with the highest possible ROI, as well as to better serve customers without having to compromise to potential fraud, as the example above demonstrates.

Retailers and massive online platforms know the value of behavioral data best: Forbes reports that 60% of Netflix rentals stem from personalized messages based on a customer’s previous viewing behavior, and 35% of Amazon’s sales are directly attributed to suggesting products an individual might like based on their unique behaviors and purchases.

Moreover, a study aimed to examine the potential revenue impact and return on investment retailers may achieve by using behavioral marketing technology found that on average, organizations can achieve 15% revenue lift over a three-year period.

Marketing is probably the most avid benefactor of behavioral data, largely because of the longest history of using it. Details of every element of online behavior have built the wealth of a few well-known corporations that are now able to use that data to effectively diversify businesses into other areas. Every click and every second spent online has a commercial value.

Behavioral data, however, has also found an interesting application in the next generation of security and authentication solutions – behaviometrics.

Neil Costigan, CEO of a Nordic biometrics startup BehavioSec, broke down some elements of one’s behavior to bring an example of the things technology is looking at, The way you use the device. Do you zoom across the screen with the mouse and then hover over a button? Which way do you circle the cursor? On mobile devices, it would also be the depth of touch, how you move your finger across the screen, how much of your finger is on the screen, how hard you’re pressing, the angle you hold the phone and so on.

Behaviometrics solutions are able to create a highly accurate and precise picture of the user by examining a range of behavioral patterns, actively evaluating the user’s unique kinetic interaction signature with their mobile device, as noted by another company operating in the field, Zighra.

The strongest authentication schemes will always make use of multiple factors, i.e., something I know, something I have and something I am, said Stephen Cox, Chief Security Architect at SecureAuth, one of the leading companies in adaptive access control and management solutions.

One of the most important hallmarks of behavioral biometrics is that powered with learning capabilities, they are able to continuously improve the accuracy, learn a wide variety of pattern elements of a particular user and everything in the background, dynamically improving the security layer, and enriching the user/customer profile for a better understanding and service tailoring. Estimates suggest that personalization can deliver five to eight times the ROI on marketing spend and lift sales 10% or more.

Fortunately, modern digital tools have infinitely expanded the universe of touch and interaction points between brands and consumers. It has never been easier to collect data, and businesses were never as capable of driving valuable knowledge from behavioral data that they are today. In the insurance industry, for example, links between insurers’ IT systems, customers’ smartphones and connected devices in cars, homes, and workplaces now enable more product and service innovations, not just a convenient channel to interact through, professionals emphasize.