Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

How EDA Technology Is Catching Fraudsters in the Act This Holiday Season

The retail holiday season is now upon us. Although Black Friday, Cyber Monday, and other big shopping events have already taken place, the year-end months still pose great threats and opportunities for festive fraud. The upsurge in shopping, combined with the increasing number of payment channels, and an advanced omnichannel offering has opened the floodgates for fraudulent activity against retailers and their customers – and the modernization of payments must happen sooner rather than later.

The solution to secure payment processing requires the digital helping hand of Event-driven architecture to protect consumers and business reputations.

Catch them in the act!

November and December represent the busiest time of the year – for retailers and fraudsters. While these year-end months represent as much as 20% of annual sales, the perfect scenario for fraudsters to attack is clear – the more spending, the more risk.

And this year, retailers and consumers need to be on high alert. Research into this year’s holiday season highlights that consumer purchasing will reach pre-pandemic levels, as consumers prepare to “holiday like its 2019”.

But, when compared to previous holiday seasons, the issue is put into perspective. In 2022, the average number of suspected digital fraud attempts on any given day between Thanksgiving and Cyber Monday 2022 was 82% higher globally than during the rest of the year, and 127% greater than during the rest of the year for transactions originating in the United States. 

Omnichannel Offerings and Surges in Payments Create the Perfect Fraud Storm

McKinsey charts a rise in fraud in a recent article series: “Skyrocketing levels of fraud, enabled by the accelerated adoption of digital commerce and the ever-increasing sophistication of fraudsters, have overwhelmed traditional controls in recent years. This surge has increased fraud losses and damaged customers’ experience and trust.”

New research by Au10tix has revealed that organized crime within North America is on the rise – the report finds a 44% increase in Q2 of 2023, with the payments sector being an attractive market for scammers after it experienced 32% of attacks.

Fraudsters Act Quickly, so Make Sure You’re Quicker

Now let’s combine this with the exponential growth in the number of payment channels and the rise of the omnichannel experience. The time it takes to settle a transaction has gone down from days to minutes. This is at a time when retailers have been forced to adapt to upwards of 10-15 different payment methods within their organization, in-store and online. The more channels, the more vulnerable the system becomes to fraudsters and criminals. 

The double-edged sword for retailers becomes clear. They must prioritize mitigating criminal activity for the safety of their consumers and their reputation. But they must do this without adding any friction into the lucrative shopping experience that would put off or dissuade purchasers of their products and services. 

Keeping a Real-Time Pulse on What’s Happening Within the Business, at All Times

Retailers need a solution that can not only keep pace but can carry out additional checks in real-time and across systems.  The possibility for fraudsters to get through the cracks is huge. 

In the real-time world of today, retailers need a real-time solution. Enter the new generation of event-driven architecture (EDA).

Detect, Action, and Stay Ahead of the Rest: Three Areas Eda Is Making a Difference

There are three key areas where technology, and EDA in particular, can help address growing fraud threats: 

  • Detect: Learning by their ‘mistakes’. Retail organizations must be able to quickly identify and action these fraudulent or criminal transactions, across all channels. Many are turning to data modeling Artificial Intelligence (AI) and Machine Learning (ML) that can learn to recognize questionable transactions. But this can be further enhanced with EDA to manage fraudulent transactions at scale
  • Action: We’re all in this together. The challenge for organizations is feeding transaction data, in real-time, to the AI/ML processes which often live in the public cloud. This is where EDA provides the real-time integration allowing legacy core-mainframe systems to communicate with modern micro-service payment frameworks and cloud-based AI/ML for fraud
  • Stay ahead of the rest: He who dares wins. EDA and the Event Mesh allow flexibility in how software components are wired together, and also flexibility in where they are located. This enables the platform to ‘evolve’, and to react quickly and effectively to any changes. Flexibility, or ‘re-wiring’, and platform evolution need to be a ‘business as usual’ activity as fraud and fraud detection is a constantly evolving game, where organizations are pitted against criminals. Who can act the fastest, wins…

The First Step: Building a EDA Technology Model

The sort of activities that go into building a fraud prevention model using the setting of trigger points would include: the type of transaction vs. is consistent with a customer’s previous transaction history.

Is it in an expected geography?

If they travel a lot, then is the time and travel distance between their last transaction and this transaction reasonable?

Related Posts
1 of 9,678

All this data must be fed into the model and assigned a score.

The score also depends on authentication requests.

So typically, if you can identify a user together with their mobile phone, retailers (and/or their banks) may pass the transaction because they are comfortable they know who the user is. But if a similar scenario occurs where the user has reached the same score, yet there is no biometric data or mobile authentication, then this would be highly likely to trigger a different reaction – blocking or flagging the questionable transaction for escalation. 

Top AIThority News: ML-Powered Efficiency: Aira, VMware, and Broadcom’s 5G Network Management

The Second Step: It’s Time to Train

Once the database of models has been built, new transactions can then be checked against the model and given an accumulated score. It’s time for AI and machine learning to step up to the plate. These technologies, aided by EDA technology, can make rapid decisions and enable companies to flag abnormal transactions in real time across all channels.

Layering these data models with AI/ML provides the opportunity for organizations to get out in front and gain ground on fraudsters. But, to be fully effective, AI/ML needs a big data set. They can only make decisions based on access to historical datasets. So, the first action is to ‘train’ the model by buying data or scraping from historical datasets. Then the model runs through several fraudulent transactions, so it is now ‘trained’ on what a fraudulent transaction looks like. The objective is to build an understanding so the AI/ML can pick out the right activities to be flagged.

EDA Remains on the Constant Lookout

Layering EDA on top allows retailers to build an enterprise IT architecture that lets information flow between applications, microservices, and connected devices in a real-time manner as events occur throughout the business.

Once the fraud model has been implemented across all transactions and payment channels, event-driven architecture then proves its worth. It enables the organization to leverage its fraud model and use AI/ML technology in real-time across an ever-expanding number of payment channels.

Read More: Impact Of AI In Fashion Retail 

Now Meet the Event Broker!

A retailer has to make sure a payments channel just sends the right event to communicate with the fraud detection system and receives the same events to get the “yes or no” back. Enter the middleman, the event broker.

Event brokers enable what’s called loose coupling of applications. This is essential because it means applications and devices don’t need to know where they are sending information, or where information they’re consuming originates. But the event broker does. 

Move Aside APIs, Your Days Are Numbered – The New Generation of Technology Is Here

Compare this with the traditional approach of REST APIs. In the context of retailing, REST APIs are a lot more challenging and need to be modified for every different channel a retailer has now, plus any new channels, especially e-commerce. This means retail organizations may have to change models based on not only changes in user behavior, but changes driven by new products and services or to counter new types of fraud. Simply put, every time a new channel is added, it must change the way fraud systems work, because they have to know about this other channel. 

In the EDA event-driven world, they don’t know, don’t need to know – and they don’t care! With EDA, retailers can accurately support a high volume of transactions in the quickest response time. They can balance transaction authentication and authorization with fraud detection without decreasing customer satisfaction, and route events securely across the whole payments ecosystem with efficiency.

A Nod to the Future: EDA Helps Businesses Beyond Fraud

Another major business benefit of EDA looks further than just fraud – it’s a platform that protects retailers today and in the future by enabling real-time data movement, even during the peak holiday season. 

As an approach to enterprise IT architecture, EDA does not dramatically contribute to technical debt and can help retailers include new services and link applications with speed, and at scale – ensuring they can match these agile competitors and provide customers with the instant kind of feedback they seek from their shopping services, while not being held back by large volumes of existing technical debt.

Recommended: State of Implementation of Generative AI (Gen AI) in Marketing

[To share your insights with us, please write to sghosh@martechseries.com]

Comments are closed.