ACI: Introduction to Fraud Scoring Services

March 16, 2022

Ever since the world was rocked by the COVID-19 pandemic, the rapid acceleration and evolution of digital payments has left some gaps in security. 

While merchants and banks have been all but forced to rapidly adapt to changes and adopt new payment types such as mobile wallets and QR code in order to keep up with growing demand, fraud prevention has been somewhat overlooked.

By answering consumers’ needs without considering fraud implications, financial institutions are creating new ways for criminals to exploit weaker controls. The challenge becomes less about innovation and more about protecting these new payment types and channels.

Global digital revenue grew by 58% from Q1 of 2020 to Q1 2021 alone. And while machine learning has been the staple of any strategy to prevent fraud or for Anti-money laundering (AML) purposes, it does have its limitations. Machine learning is based on predictive analytics, but predicting customer behavior is impossible.

Today’s payments can come from multiple sources and be made through almost any device. This generates a wealth of data that helps to surface new fraud patterns. Once these fraud patterns emerge and financial institutions create new services to meet consumer demands, machine learning models begin to degrade. Financial institutions are forced to play catch up, spending time and money re-training and re-deploying the models. To combat this, ACI is introducing Fraud Scoring Services, a fully managed subscription service in which machine learning models are managed with our patented incremental learning technology, alongside a financial institution’s pre-existing fraud prevention software.

Incremental Learning

In a few words, incremental learning is a sort of self-update for traditional machine learning models in order for it to keep up with fraud patterns as new data comes in. This way, merchants, banks or financial institutions do not have to invest resources in retraining their existing machine learning models.

Incremental learning technology will allow a model to refresh or update itself within two hours.

Testing has shown this new technology allows merchants to keep up with growing demands and prevents up to 35% more fraud, furthermore, the technology not only holds, but improves over time compared to other methods. patterns as new data comes in. This way, merchants, banks or financial institutions do not have to invest resources in retraining their existing machine learning models.

Incremental learning technology will allow a model to refresh or update itself within two hours.

In our tests, incremental learning model performance was maintained or even improved over the course of 13 months, compared with just three months for traditional models.

In this growing market, digital solutions are more important than ever in order to keep up with demand and prevent fraud across all sectors. 

Want to learn more? Check out ACI Worldwide’s full write-up here.

Share your thoughts on our LinkedIn page.

SMEs: Analyzing 2023 And What to Expect in 2024

SMEs: Analyzing 2023 and what to expect in 2024 January 3, 2024 We start 2024 reflecting back on the last year and looking forward to ...
Read More →

Mobile Payments: Will They Dominate The Market?

The idea of a comprehensive digital ID looks like the solution, but there’s much work to do in regards to implementing it. Such as which ...
Read More →

The Future is Phygital

The Future is Phygital December 20, 2023 As with many other aspects of life, the COVID-19 pandemic affected the payments landscape in terms of the ...
Read More →
Scroll to Top