Payments and risk industry veteran Kevin Sprake joins The Fraud Practice as the company’s new Managing Partner where he will continue to expand client relationships and advance the online learning and professional certification programs created specifically for the eCommerce payments and fraud prevention industry.
One of the most common reasons organizations fail to realize significant improvements in risk management after implementing custom modeling solutions can be described with one phrase: Junk in. Junk out. This article discusses best practices as it relates to data management and other factors that are shown to improve performance when it comes to custom modeling and machine learning or artificial intelligence.
It’s not just breadth of data, but also quality of data, that is important. One of the biggest misconceptions about machine learning (ML) and artificial intelligence (AI) is that you can just flip a switch and let the technology work its magic.
While there is value in leveraging Artificial Intelligence for modeling and analytics to detect cyber threats and fraud, security professionals are still more likely to indicate that a human touch is more valuable. A recent survey found that half of organizations are making use AI or machine learning but 60 percent put more trust in findings verified by humans. Meanwhile, changing consumer patterns and the rush to work from home in response to the pandemic has likely led to higher rates of false positives.
This isn’t to say AI and ML are not important – they are. In the same survey, 65% said these tools allow them to focus more on preventing cyber attacks than before and 40% reported feeling less stress.
PayPal completes their fifth acquisition in the past 12 months, this time purchasing machine learning fraud prevention provider Simility for $120 million. PayPal COO Bill Ready says each of these five recent acquisitions are part of the company’s effort to strengthen the services they provide to merchants.
Simility was founded in 2014, they are based in Palo Alto and provide advanced risk analytic and modeling solutions for fraud prevention in the Customer Not Present (CNP) channel. Major clients include eBay/StubHub, Dick’s Sporting Goods and OfferUp. The fraud prevention provider had previously raised $25 million, including PayPal as one of their early investors.
Multiple studies and sources are coming to the same conclusion: organizations will be spending more on risk management and data analytics to keep up with growing fraud and business trends. This includes $9.2 billion spent on online fraud prevention services, $170 billion spent on cybersecurity and over $200 billion spent on big data analytics globally by 2020.
With payment and online fraud continuing to increase globally, Juniper research predicts annual spending on online fraud detection services across eCommerce merchants and financial institutions will reach $9.2 billion worldwide by 2020. This is just one aspect of risk management that online merchants and financial institutions have to deal with. Gartner estimates the global cybersecurity market exceeded $75 billion in 2015.
Because eCommerce fraud is already painful with the reversal of funds, chargeback fees and lost product, the indirect costs are often ignored or are just an afterthought. Recent studies show the lasting impact payment fraud has on consumers, merchants and issuers, indicating that the cost of fraud continues beyond the initial loss. Increasing fraud has also influenced organizations’ budgets, with chargeback and risk management costs representing as much as twenty percent of a merchant’s operational expenditure, according to Javelin Strategy and Research.
Polling consumers in early 2016, a recent study found that consumers have lasting reactions after experiencing fraudulent charges on their credit or debit cards that can impact either or both the card issuing bank and merchant involved.
If you are attending the CNP Expo May 18-21 then be sure to see The Fraud Practice at booth number 418 in the Exhibit Hall. For those who would like to find out more about our online training certification programs, we will be giving out free copies of David Montague’s Essentials of Online Payment Security and Fraud Prevention book with valuable online training discount coupons inside.
There are a limited number of books available, so be sure to stop by The Fraud Practice’s booth before we run out. In addition to visiting us at the booth, you may want to attend the May 20th breakout session titled Fraud on the Move, moderated by The Fraud Practice’s Justin McDonald, Sr. Risk Management Consultant.
If you’d like to schedule a time to meet with one of our consultants at the CNP Expo, or just be sure we hold you a copy of the book, please contact us today.
If you haven’t yet registered for the CNP Expo and would like to attend, you can use The Fraud Practice’s discount code below.
It can be difficult for merchants to really understand how well they are performing with manual reviews for online fraud management relative to their peers. In this FraudBlog post we look at merchant reported statistics from three surveys covering merchants of all sizes in North America and the United Kingdom highlighting major differences between high and low revenue e-tailers.
One key metric is the manual review rate, or number of transaction attempts that are queued for a manual review. This varies greatly by merchant volume as merchants processing tens or hundreds of million transactions per year cannot feasibly review a high portion of order attempts. Many start-up and smaller merchants, on the other hand, may review nearly any transaction that isn’t squeaky clean.
Whether an organization is building a custom modeling solution in-house, using a service provider or combining both in-house and third party resources, the fundamental components of an effective custom modeling solution are the same. Statistical models must first be created, which requires historical data, a team of modeling experts, as well as the right tools and software to design effective models. Next, the organization will need the infrastructure or platform to actually apply this model to live transactions, interpret the results and route the transactions accordingly. A commonly observed problem in the market, however, is that organizations put forth such great effort in ensuring the statistical models are accurate predictors of risk that the next step, how these models are actually deployed, is often overlooked or just an afterthought.
This isn’t to say that model design is not a critical step. What’s the good in efficiently deploying custom models if they are not effective at distinguishing fraudulent from legitimate transactions? But organizations must also consider the other side of the coin: even if a custom model was accurate at predicting fraud most all of the time, it is of no benefit unless it can be applied to transactions, meaning the transactional and customer data can be fed to the models and the results can be interpreted to decide the course of action for each order.
Deployment is the second major step in executing custom models after model design, but is at least equally as important of a step.
The Fraud Practice is hosting a webinar at 1pm ET on December 4th accompanying the new white paper titled “Enabling Custom Modeling & Analytics for The Modern eCommerce Merchant” which will be released the same day.
The eCommerce market has continued to mature over recent years to the benefit of both consumers and businesses that transact in this channel. As a result new markets and services have been created while existing markets have evolved and grown. Not long ago, any business seriously considering custom models would have found it expensive, timely and somewhat difficult to put in place, so the concept of implementing custom models was left for large financial and retail organizations that had the resources to afford the cost and teams that could support the models. This is no longer the case today, however, as the maturation and growth of these services has made custom modeling and analytics much more accessible and attainable to a far greater population of eCommerce merchants.
All who register for the live webinar will automatically receive a copy of the new white paper from The Fraud Practice prior to the webinar start time.