The retail sector has seen many fraud point solution providers and fraud platforms enter the market over the last several years. But it seems very little progress has been made in both reducing fraud and also in reducing false declines.
Account opening fraud is a rapidly increasing challenge for issuers due to the plethora of identity data available to fraudsters. The 2018 Identity Fraud Study by Javelin Strategy & Research shows that the number of identity fraud victims increased by eight percent in 2017, with the amount stolen totalling $16.8 billion.
Account takeover, where a fraudster gains access to a victim’s account, typically leads to unauthorized fraudulent transactions. Account takeover fraud (ATO) is still trending upward, especially in the financial services sector. According to Javelin, existing account takeover fraud tripled in 2018 to 1.5% of all US-based consumers.
As both issuers and merchants have added more fraud layers to protect the consumer and the organization from fraud, good transactions are wrongly rejected due to suspicion of fraud arising, leading to customer loss. When a false decline takes place, cardholders may abandon a purchase altogether, seek another store to purchase at, or begin using another card entirely. False declines, therefore, lead to monetary loss, opportunity cost and reputational damage.
Aite estimates that in 2016 in the US, false declines were at USD $264 Billion and trending to $331 Billion in 2018.
Some of the top organizations have invested in point solution providers for behavior analysis, device intelligence, social reputation, email reputation, and bot and malware detection. From these providers, organizations typically receive a risk score or a rules-based approach, and often a set of data attributes as well.
It isn’t necessarily a bad investment to add new point solution or data providers as long as you are getting value out of these investments. However, that is often the hardest determination to make. Even when large organizations invest in the latest solutions, they often never fully realize the potential of their investment.
Often there is no cross-channel communication and no central decision platform for authentication or identity decisions. Each channel is working in its own silo as is each point solution provider with their scores and rule sets. And from a consumer view, they must prove their identity or authenticate across different lines of business or for different types of transactions. It starts to be obvious why we are losing the battle against fraud with this approach. Many systems, many rules, many scores, no central decision-maker or analysis to determine the optimal blend of accurate decision, cost, and performance.
With several point solution providers, each with its own rules and scores, it is challenging to build a view across all of these to make a final real-time decision on a given use case. There needs to be a single decision system that can ingest all the data from these platforms into single risk analysis, at a specific point in time, for a specific use case. And that system can also determine when call outs for additional data are necessary.
Artificial intelligence and more specifically true deep learning-based machine intelligence is creating a competitive advantage for early adopters, by adapting faster to new fraud techniques and creating a better customer experience resulting in more approvals and fewer false declines.
Machine learning can ingest existing large data sets and point solution provider scores, and in turn, provide an enhanced real-time decision. Specifically, to combat multiple types of fraud while balancing false declines, machine learning platforms are able to solve for the typical silo-based view of customer interactions across channels, connecting authentication, device, behaviour, and transaction data for intelligent inference-based decisions across customer interaction points.
What is likely missing in most organizations is the real-time ingestion of all of these scores, rules and data sources to provide more insight into consumers, merchants, and devices.
And, what is also often the case is the lack of intelligence to take action on that data. Given whatever data signals and risk systems you have in place, you should use AI inference based decision making to analyze that data and apply past known fraud or failed authentication attempts against those scores and data elements to see what fraud patterns your current platform is failing to detect and at what rate you are falsely declining legitimate transactions.
It is necessary to apply tools such as artificial intelligence to assess what data elements and risk scores correlate most significantly to fraud. You are essentially using the power of artificial intelligence to determine what data and what point solution providers are useful and what is not. As you assess the correlation of risk scores to each other, you may find that some point solution providers are adding very little lift to the decisions, which can result in a cost savings by reducing the use of these vendors. In the end you need to determine the appropriate set of authentication and identity verification mechanisms given financial costs and benefits, particular to each use case and transaction type.
AI is able to incorporate and analyze new data sources to determine if they provide more insight into risk decisions. But before adding another point solution provider, another risk score, another data source, organizations should ensure they have maximized the use of the data they already have. Before adding another point solution provider or data source, organizations should test the providers “lift” over their current sources in a proof of concept using artificial intelligence
It is tempting to add the latest innovative sounding fraud solution when you are experiencing fraud issues. But it is more important to analyze that your organization has integrated its solutions properly and has maximized its current data sources before adding another solution to the mix. Often the problem lies in the decision making across many providers, rules, and risk scores, and true machine intelligence is necessary to make sense of this complex environment and make accurate real time decisions to prevent fraud and false declines.