• Latest
europe from space

Influencer Insights: ACI Worldwide

May 6, 2020
10 Best OSINT Tools

10 Best OSINT Tools

August 15, 2022
How Print on Demand Companies Can Prevent Chargebacks

How Print on Demand Companies Can Prevent Chargebacks

August 11, 2022
KYC & AML: Know your customer and anti-money laundering explained

KYC & AML: Know your customer and anti-money laundering explained

August 7, 2022
New Podcast Episode: Walls of Thieving Cellphones with Nethone

New Podcast: How Consumers React to Identity Theft and Account Takeover Attacks

August 2, 2022
The Best Reverse Email Lookup Tools in 2022 (with pricing)

The Best Reverse Email Lookup Tools in 2022 (with pricing)

August 16, 2022
Tailgating Attack

Tailgating Attack

July 24, 2022
80 billion Euros lost to online fraud across physical and digital goods, and e-ticketing in 2021, reveals Fraugster’s new Payment Intelligence Report  

80 billion Euros lost to online fraud across physical and digital goods, and e-ticketing in 2021, reveals Fraugster’s new Payment Intelligence Report  

July 20, 2022
Influencer Insights: Christian Mangold, CEO of Fraugster Discusses the Payment Intelligence Report 2022

Influencer Insights: Christian Mangold, CEO of Fraugster Discusses the Payment Intelligence Report 2022

July 20, 2022
New Podcast Episode: Walls of Thieving Cellphones with Nethone

New Podcast: Let’s Get Megan a Job! LinkedIn recruiter scams & how to find work in the fraud prevention industry

July 19, 2022
Reverse Email Lookup to Protect Against Fraud

Reverse Email Lookup to Protect Against Fraud

August 16, 2022
Silverfort Raises $65m Series C for World’s First Unified Identity Threat Protection Platform

The Worldwide eCommerce Fraud Detection & Prevention Industry is Expected to Reach $83.9 Billion by 2026

July 15, 2022
The fraud detection and prevention (FDP) market to surpass $100 billion by 2027

Pre-hijacking Account Takeover Fraud

July 14, 2022
  • Contribute
  • Contact Us
  • About
  • Join Us
  • Advertise
  • PaymentsReview.com
Tuesday, August 16, 2022
Merchant Fraud Journal
  • Home
  • Articles
    • Chargebacks
    • Fraud Prevention
    • Influencer Insights
  • Resources
    • Recorded Webinars
    • Podcasts
    • Vendor Directory
    • eCommerce Fraud Reports
    • Training and Certifications
    • Jobs Board
    • Associations and Non-Profits
  • News
No Result
View All Result
  • Home
  • Articles
    • Chargebacks
    • Fraud Prevention
    • Influencer Insights
  • Resources
    • Recorded Webinars
    • Podcasts
    • Vendor Directory
    • eCommerce Fraud Reports
    • Training and Certifications
    • Jobs Board
    • Associations and Non-Profits
  • News
No Result
View All Result
Merchant Fraud Journal
No Result
View All Result

Influencer Insights: ACI Worldwide

by Bradley
May 6, 2020
in Articles, Influencer Insights
europe from space

europe

ACI WorldWide is a leading global payments provider. We sat down to discuss their new, patented Incremental Learning approach to building machine learning models to fight eCommerce fraud.

Incremental learning innovates on traditional fraud models by providing the algorithm with new data every 24 hours–which allows it to spot new fraud patterns as the occur.

Our discussion includes evaluating fraud models for degradation, the flaws in the traditional machine learning model, and more.

1. ACI’s incremental learning is centered on the idea of fraud models degrading over time. How long do merchants’ fraud models last on average? How can you evaluate for degradation, before it becomes apparent via chargebacks? 

All models degrade over time. How long the models last depends on a number of variables including the merchant’s industry, purchasing channel, season, etc… We’re seeing frequent changes in fraudulent behavior, more so than before; So it is important to be able to take an approach to ensure that these changes do not lead to model degradation. ACI’s incremental learning approach is able to recognize these small but frequent changes and, if required, make adjustments to the production model without requiring retraining or redeploying the production model. 

2. What do you estimate the practical effect of incremental learning to be in terms of chargeback rates and false positive declines versus traditional machine learning models?

Any degradation of model performance will increase the amount of chargebacks incurred. Incremental learning is about maintaining performance at a high quality for longer periods of time without negatively affecting false positive rates. In testing it was shown that within three months our models saw the benefits of incremental learning. This translates into a lot of savings in time and effort for the merchant. Most importantly, it performs better than traditional machine learning methods.

3. You filed for a patent for incremental learning in January. Can you share what makes the technology unique enough that it required one?

The ability to take an existing model and maintain performance for longer periods of time, by actively looking for anomalous behavior incrementally over shorter periods of time is a new approach to tackling the ever-changing fraudulent behaviors that are seen. Incremental learning is autonomous, which moves fraud prevention from predictive to being prescriptive. Having a seamless approach that identifies and adapts to new behaviors without intervention is a step forward in fraud prevention.

4. The traditional machine learning model vaunts itself as benefiting from a long and coordinated order review history across the merchants in the network. Is incremental learning saying that model is fundamentally flawed?

Traditional machine learning approaches are here for the foreseeable future. The power of historical consortium data is fundamental to machine learning, ours as well as every other solution. Where incremental learning fits is to take a traditionally trained model and maintain its performance for longer periods of time. This is done by looking at data over shorter intervals and, if required, make changes to the production model without having to retrain a new model.

5. Incremental learning ‘adjusts to new behaviors’ within every 24-hour time frame. Can you give a hypothetical example of how the model might adjust based on new inputs, and how the adaptation would produce better results than a traditional machine learning model?

Traditionally, machine learning models are trained on large amounts of historical data that is labeled. Each 24-hour period adds new information that is valuable and sometimes critical to the performance a fraud prevention model. The benefit of incremental learning is that you avoid retraining the model on the expanded data set and only require to learn from the last 24 hrs of data. The model in production can then be updated with the new learnings without a requirement to redeploy.

6. Is there a risk that changes seen over just a 24-hour period might cause models to readjust too quickly to an anomaly (say, a single, massive attack by a fraud ring) and risk sub-optimal results in the future? What if the data from two separate 24-hour periods diverges significantly?

Incremental learning does not hastily make decisions and instead gradually morphs to the changes it sees in each 24-hr period. We at ACI also use a multi-layered approach to fraud prevention, where incremental learning is a part of the machine learning layer. These layers, along with our highly skilled and experienced data scientists and risk analysts work together to create strategic rules that protect our customers from singular fraud ring-related events. 

7. You write that incremental learning models don’t need to “re-learn everything they already know”. Can you give a practical example of how this is an improvement on standard machine learning models? 

The improvement is similar to how we use information ourselves. When we learn something new, we do not have to re-learn everything we knew. We take the additional learnings and use them to make informed decisions. This is what incremental learning brings to machine learning. The new behaviors observed are used in conjunction with what the model had been trained on previously to make better predictions against fraudulent transactions. 

8. Is there any performance or storage cost benefit to reducing reliance on historical data?

Storage can be quite expensive and storing large amounts of data for the purposes of retraining models can lead to additional costs that build up over time. Incremental learning does not require the initial dataset once trained. The main concept of online ML algorithms is that each transaction is only used once and then discarded, thus we can achieve both performance and storage cost benefits simultaneously. 

9. You cite “[reducing] the number of model deployments required for our customers” as one of incremental learning’s advantages. Can you give an example of when/how a merchant would benefit from this? 

Model performance can degrade over time. This degradation can be due to several factors, such as change in fraud behavior observed. Incremental learning keeps model parameters up to date, allowing a reduction in the number of deployments over longer periods. The ability to morph the model gradually based on new learnings from the last 24 hrs is a key component of Incremental Learning. This keeps you from having to retrain and deploy a new model 2-3 additional times each year, saving time and effort of skilled personnel at the merchant.


Jimmy Hennessy

Director of Data Science

ACI Worldwide

https://www.linkedin.com/in/jimmyhennessy/

Mr. Hennessy leads a team of data scientists at ACI who are dedicated to safe guarding merchants against fraud.  He is a seasoned veteran with 18 years’ experience within computer and data science with a proven track record of successfully helping clients.

Tags: Incremental LearningMachine Learning
ShareTweetShareSend
Previous Post

Clearsale On Ecommerce Fraud & COVID-19

Next Post

Share your feedback for a chance at a $25 Starbucks gift card.

Next Post
Ecommerce Fraud Trends 2020 Report Released

Share your feedback for a chance at a $25 Starbucks gift card.

Our Sponsors

Our Latest Report

Get the 2022 Fraud Trends Report

MFJ 2022 Fraud Trends Report

Search Our Site

No Result
View All Result

Featured Directory Listings

  • logo
    NoFraud
  • Microsoft Dynamics 365 Fraud Protection
  • Ekata
  • Pipl
  • nSure.ai logo
    nSure.ai
  • sift logo
    Sift
  • Spotrisk
  • SEON. Fraud Fighters
  • PayRetailers

Our Sponsors

Fraud Industry News

10 Best OSINT Tools

10 Best OSINT Tools

August 15, 2022
How Print on Demand Companies Can Prevent Chargebacks

How Print on Demand Companies Can Prevent Chargebacks

August 11, 2022
KYC & AML: Know your customer and anti-money laundering explained

KYC & AML: Know your customer and anti-money laundering explained

August 7, 2022

Connect With Us

Quick Navigation

  • Home
  • News
  • Join Us
  • About Us
  • Contact Us
  • Advertise
  • Contribute
  • Privacy Policy

The Payments Media Network

Merchant Fraud Journal
Payments Review

Privacy Policy

Our Privacy Policy
Our Terms of Use

Resources

  • Articles
  • eCommerce Fraud Reports
  • eCommerce Fraud Webinars
  • Training and Certifications
  • Jobs Board
  • Associations and Non-Profits
  • Podcasts
  • Vendor Directory

Popular Posts

  • How Does Two-Factor Authentication (2FA) Work?

    How Does Two-Factor Authentication (2FA) Work?

    0 shares
    Share 0 Tweet 0
  • How to File a Claim With FedEx + What To Do If Claim is Denied

    0 shares
    Share 0 Tweet 0
  • Top eCommerce Fraud Prevention Companies

    0 shares
    Share 0 Tweet 0
  • How to Fight PayPal Chargeback Fraud

    0 shares
    Share 0 Tweet 0

Featured Vendors

  • PayRetailers
  • Spotrisk
  • Sift
  • NoFraud
  • nSure.ai
  • Pipl
  • Microsoft Dynamics 365 Fraud Protection
  • Ekata
  • SEON. Fraud Fighters

Download the 2022 Fraud Trends Report

No Result
View All Result
  • About Merchant Fraud Journal
    • Advertise on Merchant Fraud Journal
    • Interested in Contributing or Guest Posting to Merchant Fraud Journal?
  • Articles
    • Chargebacks
    • Fraud Prevention
    • Influencer Insights
  • Contact Us
  • Download Addressing Payment Fraud and Customer Experience Report
  • Download Evolving Complexities of Payment Fraud Report
  • Download the 2020 Chargeback and Representment Report
  • Download the 2020 Merchant Fraud Journal Vendor Guide
  • Download the 2021 Fraud Trends Report
  • Download the 2022 Fraud Trends Report
  • Download the 3 Ways a Unified Chargeback Management and Fraud Platform Increases Revenue Report
  • Download the MFJ 2022 Customer Experience Report
  • Download the MFJ ATO in Retail Report
  • Home
  • Job Dashboard
  • Join The Merchant Fraud Journal Community
  • Merchant Fraud Journal Advertising Agreement
  • MFJ Fraud Trends Report Giveaway
  • News
  • Post a Job
  • Privacy Policy
  • Resources
    • 2020 Chargeback Representment Guide for Merchants
    • 2020 Vendor Guide
    • 3 Ways a Unified Chargeback Management and Fraud Platform Increases Revenue
    • Addressing Payment Fraud and the Customer Experience in 2022
    • Associations and Non-Profits
    • ATO Fraud In Retail Report
    • Balancing Customer Experience and Fraud Prevention: What’s the Secret?
    • Digital Trust & Safety: Combating the Evolving Complexities of Payment Fraud
    • eCommerce Fraud Reports
    • eCommerce Fraud Webinars
    • Fraud Prevention Training and Certifications
    • Jobs Board
    • Merchant Fraud Journal’s Fraud Trends 2020 Report
    • Merchant Fraud Journal’s Fraud Trends 2021 Report
    • Merchant Fraud Journal’s Fraud Trends 2022 Report
    • MFJ’s 2022 Customer Experience Report
    • Podcasts
    • Prevent High-Velocity Fraud Attacks During the 2021 Holiday Season
    • Vendor Directory
    • Webinar – Addressing Payment Fraud and the Customer Experience in 2022
    • Webinar – Mitigating Fraud and Risk on the ACH Network
    • Win January Chargeback Disputes
  • Subscribed
  • Terms and Conditions

© 2021 Payments Media Solutions Canada Inc.

Are you sure want to unlock this post?
Unlock left : 0
Are you sure want to cancel subscription?
[class^="wpforms-"]
[class^="wpforms-"]