GS Logo
The Green Sheet, Inc

Please Log in

A Thing
View Archives

View flipbook of this issue

Care to Share?


Table of Contents

Lead Story

MLS 2.0: secure, compliant, resourceful, discoverable

Dale S. Laszig

News

Industry Update

News Briefs

Features

The Green Sheet Advisory Board What it takes to thrive in payments today - Part 3

TSG's new directory of U.S. acquirers

Views

Visa, Mastercard aim to accelerate B2B card payments

Patti Murphy
ProScribes Inc.

Education

Street SmartsSM:
Archives: Veritably valuable added services

Dee Karawadra
Impact PaySystem LLC

Legal ease: ISO contract management in the digital age

Adam Atlas
Attorney at Law

Help your merchants increase customer loyalty

Barry Davis
Womply

Three ways to take your ISO to the next level

Jordan Olivas
RS Software Inc.

Company Profile

CardX

New Products

Unified security management, compliance solution

USM Anywhere
AlienVault Inc.

Inspiration

The sales door: close it or leave it open?

Departments

Letter from the editors

Readers Speak: Machine learning can safeguard global payments

Resource Guide

Datebook

A Bigger Thing

The Green Sheet Online Edition

June 11, 2018  •  Issue 18:06:01

previous next

Readers Speak: Machine learning can safeguard global payments

Since the introduction of EMV, fraudsters have focused on card-not-present (CNP) transactions. A February 2018 study by Javelin revealed fraudulent transactions are 81 percent more likely to occur online than at the POS. This is likely attributable to the rise in online merchants and the rise of digital transactions. As, globally, we migrate to shopping online more frequently, fraudsters continue to find ways to exploit loopholes in transactions. This is where machine learning moves from a buzz word into practice.

Machine learning models can use the dollar amount of the transaction, the location and device from which a transaction is made, along with hundreds of other data points – all in real time – and establish patterns in a consumer's behavior. Each time a purchase is made, the machine learning model compares the most recent transaction characteristics to the historical profile to determine, within milliseconds, if the transaction is legitimate or suspicious. This ensures that the highest level of security is provided, mitigating risk, eliminating friction and allowing more genuine transactions to be processed.

When it comes to CNP transactions, honest players around the globe – genuine consumers, merchants, processors and financial institutions – want two things: speed and security. If an imbalance exists on either end of the spectrum, the entire transaction is jeopardized, resulting in a lost sale to the merchant and frustrated consumer. Existing fraud models capture patterns and create alerts that signal transactions that could be fraudulent. The challenge behind these indicators is that they sometimes miss new fraud because they are not self-taught. Machine learning solves for this challenge, by understanding the customer at each individual touchpoint and constantly addressing new fraud patterns. This helps eliminate false positives, ensuring the right transactions do go through, and recognizes new fraud attacks as they occur. This delivers a risk- and friction-free experience and is the only way both parties can be satisfied. The increasing reliance on speed and security leaves global payments vulnerable to fraud. Machine learning provides that extra layer of protection.

Dave Excell, Co-founder and CTO of Featurespace Ltd.

Have insights to share?

Many thanks to Dave Excell for sharing his expertise here. We will welcome your helpful perspectives at greensheet@greensheet.com.

Notice to readers: These are archived articles. Contact names or information may be out of date. We regret any inconvenience.

previous next

Spotlight Innovators:

North American Bancard | USAePay | Super G Capital LLC | Humboldt Merchant Services | Impact Paysystems | Electronic Merchant Systems