Home Internet of Things Aerospace Apparel Energy Defense Health Care Logistics Manufacturing Retail

Machine Learning Helps IoT Deliver a New Channel for a Better, More Secure Payments Experience

Faster and easier payments often come at a risk, but machine learning can simplify our understanding of those behaviors that lie outside a user's normal patterns.
By David Excell
Apr 08, 2018

More than 8 billion connected devices were reportedly in use last year, up 31 percent from 2016, according to a Gartner research report. The same report states this number will increase to 20.4 billion by 2020, with devices ranging from cars to cameras.

The numbers point to a fundamental shift in the way consumers engage and interact with each other—including the desire for more innovative ways to pay for goods and services. Businesses trying to improve their customer engagement must meet their customers "where they are," by offering preferred payment methods and ensuring these methods are both as simple and as secure as possible—historically contradictory requirements.

In an environment in which people can pay with the tap of a phone or from a wearable device, there's also an inherent consumer expectation of faster and more secure payments. Unfortunately, the fast-paced payments process is opening channels for faster fraud, with the Internet of Things (IoT) providing fraudsters with an abundance of new devices to use as channels for criminal activity.

For some industries, the growing creation and adoption of IoT devices equates to the need to further develop and execute strategies to detect and deter fraud. Enter adaptive behavioral analytics and real-time machine learning.

When looking at how behavioral analytics can assist with risk-mitigation strategies as a consumer, we can look to the example of voice-assistance technology. In a true fraud situation, if you are out of town and leave a window cracked open and your voice-activated device visible, a thief can easily order items, have them shipped to your home and pick them up before you even return. With advanced behavioral analytics, your method of payment would realize you are traveling and flag the order as fraudulent.

There are also situations which are not as nefarious, but can easily occur in the same scenario. If you have background noise while ordering windshield wipers, your technology could hear "Order baby diapers." Machine learning can pick up on your patterns and realize you don't order diapers, and alert you that this could have been an order placed in error.

While machine learning and behavioral analytics have been around for years, many industry experts are predicting 2018 will be its momentous point. According to Gartner's latest CIO survey, respondents indicated machine learning and artificial intelligence are in their top-five priorities this year, with 21 percent of CIOs from around the world testing or considering these initiatives in the short term. One quarter of the CIO respondents have medium- or long-term plans for the technology. There are many reasons behavioral analytics should be an integral part of the short- and long-term technology roadmaps, especially for financial institutions and payments processors.

Login and post your comment!

Not a member?

Signup for an account now to access all of the features of RFIDJournal.com!

PREMIUM CONTENT
Case Studies Features Best Practices How-Tos
RFID JOURNAL EVENTS
Live Events Virtual Events Webinars
ASK THE EXPERTS
Simply enter a question for our experts.
TAKE THE POLL
JOIN THE CONVERSATION ON TWITTER
Loading
RFID Journal LIVE! RFID in Health Care LIVE! LatAm LIVE! Brasil LIVE! Europe RFID Connect Virtual Events RFID Journal Awards Webinars Presentations