Written by Parul Sharma, LexisNexis Risk Solutions
As per Acquia, 90% of customers say they want convenience. 90% of customers also say that brands do not meet their expectations for a good experience. To meet those expectations, brands need to prioritize convenience when designing customer interactions. Convenience should not come at the expense of accepting more fraud because fraud is expensive. As per CFCA Fraud Loss Survey 2019, the estimated global loss in telecom sector is $28.3 billion USD. The data shows the fraud loss and impact on the rising in terms of a percentage of revenue for telecom operations. So how do we enable better customer experience without fraud? This calls for a layered approach to prevent, detect or mitigate fraud while maintaining a good consumer experience. In this article, I will talk about three major layers of defense and I recommend using them on top of each other. The order in which these layers are called can vary on the company’s infrastructure.
Consortium based digital Identity Analysis
Digital identity is the identity of the persona transacting online. In case of digital world, there is always an uncertainty on the owner of the identity. Device, personal data, IP and past behavior can be very useful in authenticating these digital identities, but to make the most use of existing personas, there is a need for consortium. My most recent fraudulent persona is your next potential fraudulent applicant and the consortium can help share these insights to reduce fraud losses. Fraud is borderless and has a strong network, consortium based digital identities can help detect fraudsters pro-actively without creating additional false positives.
Leverage machine powered insights
There is a need to combine human and machine strengths to deliver a scalable and repeatable process with the data we have. Machines are good at pattern recognition at scale and humans are good at understanding the problem, therefore a blend of both human and machine learning can increase the efficacy of current fraud management systems. Fraud trends share many similarities across industries and geographies. Industry consortium models can provide a best-practice fraud model that leverages performance from across a wider set of common customers. These models can incorporate a disparate set of risks that may not be evident to an individual organization yet. And Individual organizations can almost immediately get the benefit by leveraging identified fraud patterns in their same industry / geography / use case.
Unleash the power of passive behavioral biometrics
As per whatis.com “Behavioral Biometrics is the field of study related to the measure of uniquely identifying and measurable patterns in human activity. The term contrasts with physical biometrics, which involves innate human characteristics such as fingerprints or iris patterns.” Behavioral biometrics can help build trust relating to good customers by building strong scores over time that increases confidence in specific good behavior. This can reduce false positives by modeling behavior on a per user basis.
Layering the way, a user interacts with their device, with information relating to the trustworthiness, integrity and authenticity of that device along with power of machine learning models can form a compelling way to detect high-risk scenarios and good customer behavior accurately. Accuracy brings credibility which eventually brings more business and keeps fraud away. It’s also important to look at end to end journey while working on the layered approach to help better differentiate suspicious and good behavior to build accuracy because looking at part of the workflow can create blind spots.