As fraud professionals, it’s natural to focus on preventing fraud losses, but this often comes at the detriment of sales conversion. The nature of model-based risk management platforms and machine learning model training has this bias as well, mainly as a result of the fact that it is much easier to recognize missed fraud than it is to recognize sales insults.
This white paper examines the trends and common themes associated with merchants who thrived versus merely survived 2020 and the lasting changes on eCommerce and omni-channel retail. This includes a look at differences in risk management strategy architecture, readiness to scale and effective communication between the digital and physical worlds to support a true Unified Commerce strategy.
Fraud solution providers need to be prepared to competitively position and message against the new Amazon Fraud Detector risk modeling services. Here’s what risk vendors and sales professionals need to know about Amazon’s new risk management service offering and how to prepare for prospects or current clients considering this new service.
Fraudulent insurance claims are responsible for more than $80 billion in losses per year in the United States, leading to higher premiums for all policy holders. It is estimated that card issuers will lose $1.3 billion this year from cards issued to synthetic identities. Total fraud losses from synthetic identities receiving loans and credit cards are estimated at $6 billion annually. Lenders, issuers and insurance carriers are increasingly combating fraudulent applications and claims with custom modeling solutions and AI.
Checking pay stubs to verify income is no longer sufficient. Completing an application with their authentic identity, a consumer can easily fabricate paycheck stubs or purchase them online for less than ten dollars. When fraudsters create synthetic identities to take out an uncollateralized loan with no intention of paying it back, they can just easily create or buy fake pay stubs to corroborate their synthesized existence.
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.
How well would your fraud management program perform if your organization depended on it for doing business with customers from countries like Ukraine and Nigeria? Now what if we said your business was facilitating money remittances to these countries? WireCash is doing just that, and we sought to uncover how this could be possible by talking directly with the company that found success at the intersection of one of the highest risk industries and some of the highest risk countries in terms of online fraud.
The use of custom modeling and risk analytics also allows WireCash to be more consumer-friendly than they were in their ATMCash days, and compared to most online MSBs. While WireCash may sometimes require strong authentication or verification techniques, they try to eliminate the need for this and reduce friction for most new customers through use of risk modeling and amassing many neutral or low risk signals. They have also leveraged this experience and insight to enter new markets where others wouldn’t go or would only tread lightly. WireCash today helps consumers send money to Nigeria, Ukraine, Russia, Armenia and other countries that present high risk. Money Service Businesses providing remittances to these countries have tended to offer limited services or maintain several day waiting periods.
In mid-January IBM announced the acquisition of IRIS Analytics, a data modeling and analytics provider based in Germany that focuses on risk management for issuers and payment providers. This is IBM’s second acquisition in risk management for the financial services industry following their 2013 purchase of Trusteer.
IRIS Analytics was founded in 2007 and provides a data modeling and analytics platform with real-time risk scoring to support payment card and mobile payments. The acquisition will bolster IBMs fraud prevention and eCommerce services, complimenting their IBM Security Trusteer Advanced fraud protection solutions.
Real-time custom modeling can enhance Business Intelligence capabilities leading to not only improved risk detection, but an overall better understanding of your customers and business, which benefits other areas of the business outside of risk management. Many of the capabilities and features to look for when building or buying custom modeling solutions for risk management also contribute to the ancillary benefits a risk-focused custom modeling solution may offer in other departments or groups, such as marketing and front-end or user experience analytics.
This feature article from The Fraud Practice specifically discusses the critical capabilities organizations should build or look for if they want to leverage custom modeling solutions for effective Business Intelligence, both as it pertains to risk management and other aspects of a business.
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.