Consumers use many accounts for financial transactions, ordering products, and social media—a customer’s identity can be stolen using any of these accounts. Identity fraud can happen when setting up or using financial accounts, but it can also occur with communications such as audio, images, and chats.

According to Business Wire, “While total combined fraud losses climbed to $56 billion in 2020, identity fraud scams accounted for $43 billion of that cost. Businesses need to have a way of protecting their users even when their identity has been compromised.”

“With the exponential growth of customers’ digital transaction data, the traditional rule-based fraud detection methods are having increasing difficulty meeting the requirement. Artificial intelligence (AI) can augment the existing rule-based models and strengthen human fraud analysts significantly, which can improve accuracy and efficiency while reducing costs,” states Meng Lie, Analyst, Forrester.

What Are Identity Theft and Identity Fraud?

According to the US Department of Justice, “Identity theft and identity fraud are terms used to refer to all types of crime in which someone wrongfully obtains and uses another person’s personal data in some way that involves fraud or deception, typically for economic gain.”

How cloud-based, GPU-accelerated AI meets identity fraud needs

Artificial intelligence (AI), machine learning (ML), or deep learning (DL) models are increasingly being used to analyze transaction and login data to help protect customers and financial organizations from identity fraud. AI models can analyze large volumes of data and recognize anomalous patterns in that data suggesting fraud.

Running AI models used in identity fraud prevention requires huge computational resources. NVIDIA graphics processing units (GPUs) provide processing power for AI, ML, or DL models that cannot be matched by central processing units (CPUs).

Microsoft and NVIDIA have a long history of working together to support financial institutions in detecting and preventing fraud. Using Microsoft Azure cloud and NVIDIA AI provides scalable, accelerated resources needed to run AI/ML/DL algorithms, routines, and libraries.

The partnership between Microsoft and NVIDIA makes NVIDIA’s powerful GPU acceleration available to financial institutions. Azure supports NVIDIA’s T4 Tensor Core Graphics Processing Units (GPUs), which are optimized for the cost-effective deployment of machine learning inferencing or analytical workloads. The Azure Machine Learning service integrates the NVIDIA open-source RAPIDS software library that allows machine learning users to accelerate their pipelines with NVIDIA GPUs. The NVIDIA platform provides powerful adaptive AI inferencing tools to identify fraud patterns in massive volumes of data in real time.

Trends in AI usage to prevent fraud

According to Kevin Levitt, NVIDIA Director of Industry and Business Development for Financial Services, “Financial institutions will invest heavily in AI to fight fraud and adhere to compliance regulations such as KYC (Know Your Customer) and AML (Anti-Money Laundering). Some are using a customer’s unique voice to authenticate online transactions, while others are turning to eye biometrics for authentication. Graph neural networks are at the forefront of the new techniques AI researchers and practitioners at financial institutions are using to understand relationships across entities and data points. They’ll become critical to enhancing fraud prevention and to mapping relationships to fight fraud more effectively.”

Microsoft Solutions to Prevent Identity Fraud

Microsoft Dynamics 365 Fraud Protection is a product created by Microsoft as a comprehensive fraud protection solution. Microsoft Dynamics 365 Fraud Protection and Microsoft Azure Active Directory work well together to provide customers a comprehensive authentication seamless access experience. Important fraud discovery and prevention techniques incorporated include:

• Device fingerprinting: The tool uses device telemetry before a customer logs in or accesses an account to identify the device that is being used with hardware information, browser information, geographic information, and the Internet Protocol (IP) address. This information can be compared against the computer system typically used by the customer.
• Bot detection: Advanced adaptive artificial intelligence (AI) is used to generate a score that is mapped to the probability that a bot is initiating the event rather than a person. This helps detect automated attempts to use compromised credentials or brute force Distributed Denial-of-Service (DDoS) attacks.
• Frequency of Event (Velocity): How frequently a transaction occurs helps determine if there is suspicious activity and possible fraud. For example, is a single credit card or many credit cards used from a single IP address to place many orders in a short period of time?
• Account protection: Adaptive AI helps a merchant determine if a bot is using automated attempts to create fake accounts or to compromise existing accounts. The AI solution provides a score that maps to the probability that a bot is initiating the event. Merchants can use the score with the rules they’ve configured to block automated fraudulent account creation and login attempts or add another method of verification on suspicious attempts such as sending an automated text, chat, or phone call to the customer.
• Risk-based Authentication: Most users have a normal behavior that can be tracked. If a user’s login is unusual, it could be risky to allow them to successfully sign in. Organizations can choose to block the login attempt or require multi-factor authentication. Azure Active Directory B2C risk-based authentication will challenge login attempts that are over the defined risk threshold while allowing normal logins to proceed unhampered.

The FIS Memento solution is also useful in locating identity fraud. This tool provides protection in real time using a combination of rules, AI, ML, and statistical techniques to detect and prevent fraud in banking and payments channels. FIS Memento is offered as an on-prem or Azure Cloud based solution.

Summary

Financial institutions need adaptive AI technology to address the ever-increasing complexity of identity fraud. Microsoft and NVIDIA provide advanced hardware, cloud, AI, and software solutions for financial institutions that locate potential identity fraud to help protect customers.