Neobanks: How AI can turbocharge your KYC process

In traditional banking, a financial institution would try to prevent financial crimes and illegal activities, such as terrorism financing, by implementing practices to meet KYC requirements. These KYC compliance measures would include physically verifying a prospective customer before they could access day-to-day services, from opening banking accounts or a checking account to acquiring new debit cards or credit cards. In financial services, the need remains to verify the identity of would-be customers, but with the growth of the digital bank worldwide, operators are looking for more innovative solutions to complete enhanced due diligence (EDD), customer due diligence (CDD), and other compliance measures.

The application of Artificial intelligence (AI) in the form of machine learning promises to be transformative for many sectors, and neobanking is no exception. By analyzing huge volumes of digital data, automated decision engines can recognize patterns and progressively improve the speed and accuracy of processes. This kind of machine learning is already being used with great success by neobanks, both to improve fraud prevention and to deliver a better user experience.

Improving accuracy

Neobanks increasingly use identity verification (IDV) for the Know Your Customer (KYC) process required by regulators to prevent money laundering. The best IDV systems compare live biometric data from a selfie with stored biometric data to authenticate customer sessions. By incorporating machine learning algorithms programmed to identify patterns into this kind of automated IDV solution, the data collected can be used to adjust and improve the accuracy of its decision-making over time. 

Because machine learning makes predictions based on previous experience, novelty is a potential blind spot for the technology. The larger and more current the dataset, therefore, the lower the risk that an automated decision engine will make a mistake. For identity verification, for example, access to a dataset that includes plentiful biometric data for a range of ethnicities and ages is important in minimizing potential bias. In addition, cross-comparing verification sessions based on device, network and customer behaviour can provide a greater richness and variety to the data a decision engine uses to learn and improve its decision making.

Ensuring a better experience for legitimate users

Another application of AI in the IDV process is assisted image capture (AIC). This uses machine learning to identify and mitigate the most common verification errors, thereby simultaneously increasing conversion rates at the same time as ensuring accuracy. AIC acts as an active photo assistant, guiding users with multiple responses to help them take better images of their identity documents and ensure success on the first try. It alerts users to a range of errors including unreadable data, incomplete documents, unclear facial images for comparison, and unsupported documents. The result is sharp, well-lit, correctly framed images of ID documents that provide all the necessary information for an automated decision engine to confirm identity verification, without the need for human intervention on the bank’s behalf. 

Maximize conversions while minimizing risk

Combining AIC with the use of machine learning in IDV decision-making lets customers verify their identities quickly and easily, while simultaneously improving accuracy. The result is a higher conversion rate, less work for support teams and an overall improvement in ROI.