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.
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.
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.
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.
Register for the webinar and white paper
More information about the white paper
In an interview with ZDNet, Josh Sullivan, leader of the data science and analytics practice at Booz Allen Hamilton, discusses the importance of human analysis complementing machine analytics. While the focus is on big data for any application, the discussion and points made provide insights and important considerations very relevant to modeling and analytics for fraud and risk management.
While card issuers and financial institutions have long employed modeling and analytics as a fraud prevention technique it is now becoming more common among eCommerce merchants. As a result we are seeing much more talk about machine learning, neural networks and advanced statistical models in the risk management marketplace. Although custom analytic modeling risk services require sophisticated platforms and technology, the reality is that a human element is required to ensure these services continue to run effectively.