Fighting financial crime with cloud and AI

Fighting financial crime with cloud and AI

Solutions like Microsoft Azure are helping banks such as HSBC rise to these security challenges

Elly Yates-Roberts |

Providing seamless, omnichannel customer experiences is essential for competitive financial business. But the digital world also brings a multi-layered challenge: safeguarding the business and its customers from relentless attempts at financial crime.

Regulators now require banks to absorb the costs of fraud for real-time transactions and processes, so the pressure is on to identify, manage and mitigate risk more efficiently. The problem is, many of the rules-based fraud prevention processes in place today are yielding over 90 per cent false positives, requiring legions of investigators to spend time manually reviewing alerts. Tightening the model to reduce the number of false positives would also increase the likelihood of missing real fraudulent activity. 

Cloud and artificial intelligence (AI) technology are the key to resolving that challenge. According to McKinsey & Co, banks that invest in data-aggregation, process automation and advanced statistical modelling using machine learning and AI can decrease compliance-error rates from over 30 per cent to less than 5 per cent and cut false-positive alerts to below 50 per cent.

Financial firms recognise this opportunity. “In the fast-changing, tech-driven world banks now live in, they recognise that technology can play a role in helping them meet both their customers’ expectations and challenging regulatory requirements,” writes Bill Borden, corporate vice president of worldwide financial services at Microsoft in an industry blog. “The industry has a tremendous opportunity to accelerate the use of cloud and AI as a catalyst to improve competitiveness, drive growth, elevate customer experiences and keep ahead of changing regulations and cybersecurity threats.”

In Hong Kong, for instance, HSBC is building new services in the cloud to enable better organisation and analysis of its data and make more core customer journeys and features available in a mobile-first environment – while delivering bank-grade security. The bank’s PayMe for Business app, built on Microsoft Azure, enables businesses to collect payments instantly and use built-in intelligence to improve sales and operations. Adopting a microservices-based architecture with Azure Kubernetes Service and Azure Database for MySQL enabled HSBC to build isolated services with stronger security and overall application up-time. A powerful analytics platform with machine learning, built on Azure Databricks, enables fast identification of customer-merchant-transaction relationships and patterns to deliver personalised customer experience, while quickly detecting anomalous activity.

One key problem for financial firms is that fraudsters continually change their techniques and try new approaches, adapting to regulatory changes faster than the business can. But intelligent applications – such as the BioCatch behavioural biometrics solution built on Microsoft Azure – are slowing down this game of cat and mouse. These tools leverage AI to study how an individual interacts with the company’s website or mobile app, from the way they hold and touch their mobile to how they correct typos. By comparing today’s interaction with this baseline, they can confirm whether it’s anomalous.

Microsoft’s own fraud detection solution harnesses AI to enable smart, near-real-time online fraud detection at scale – whether the data is on the premises, in the intelligent cloud, or at the intelligent edge of mobile apps. Financial firms can leverage Azure Machine Learning to tailor fraud detection models to their own electronic banking applications and sessions, defining and training it to match the bank’s digital solutions. By analysing application log data, transactional information and customer data from internet app-based banking and other digital channels, they can identify potentially fraudulent behaviour and evaluate real-time sessions, activities and transactions.

Microsoft Dynamics 365 Fraud Protection also enables banks and e-commerce merchants to decrease fraud costs and increase acceptance rates for customer payment transactions while providing a seamless purchasing experience. It uses AI technology that continuously learns and adapts to evolving fraudulent patterns and its Transaction Acceptance Booster feature also addresses wrongful declines.

Behind all this activity is Microsoft’s commitment to trust, security, privacy, compliance and transparency, backed by resources such as the Azure Trust Centre and Azure Security Centre.

“Because of the hyper-connectivity, we know that regulatory compliance is and must be a top priority, which is why Microsoft continues to work with financial services regulators and customers to ensure our cloud services help customers meet their strict regulatory requirements,” says Borden. “This longstanding engagement with regulators around cloud computing is one of the reasons more than 90 per cent of global systemically important financial institutions depend on Microsoft cloud services.” 

This article was originally published in the Spring 2020 issue of The Record. Subscribe for FREE here to get the next issues delivered directly to your inbox.

Subscribe to the Technology Record newsletter

  • ©2024 Tudor Rose. All Rights Reserved. Technology Record is published by Tudor Rose with the support and guidance of Microsoft.