Lloyds Bank touts quantum potential in anti-fraud activities

IBM and Lloyds Banking Group have carried out an experiment to see whether quantum computing can be used to identify money mules – and the project highlighted huge long-term potential.

The computation required in financial services, from fraud detection to optimization and simulation tasks, is getting more complex all the time. While AI and classical machine learning play a vital part, Lloyds reckons they will eventually reach a limit.

Early research from its Emerging Technology & Innovation (ET&I) team suggests several areas where quantum computing could outperform classical methods, including graph-based anomaly detection - an important element in detecting fraudulent or criminal behavior.

"Economic crime prevention, particularly the detection of mule accounts, requires analysing highly complex networks of financial transactions," explained Jamie Harbour, enterprise architect, emerging technology and innovation and Adam Milner, lead quantum ambassador at Lloyds.

"These can be represented as graphs of customers, accounts, and payments, where suspicious activity often hides in subtle network structures."

Traditional computers struggle with certain types of graph problems as the number of possible solutions grows exponentially with the size of the problem - something that quantum computing could handle more efficiently.

"Our experiment did not aim to explore how to replace machine learning models currently used in fraud and crime prevention," said Harbour and Milner.

"Instead, it explored whether quantum enhanced techniques could one day generate more sophisticated graph-based features to support future models; features that might be too complex or expensive to compute classically."

Quantum shows long-term promise

The nine‑month project focused on graph‑based analysis of mule activity, using anonymized real transaction data on IBM’s cloud quantum computers, and examined several different quantum algorithmic approaches.

The aim wasn't to deliver production-ready solutions, but to work out which quantum techniques might have genuine long-term promise.

Several quantum algorithms did, according to Lloyds, especially when used to complement AI and ML by generating new types of features or enabling deeper network analysis.

Alongside the experiment, the ET&I team also developed a broader roadmap identifying several potential quantum use cases across the Lloyds Group.

Some, such as optimization tasks, could be a realistic proposition relatively soon, thanks to the maturity of the relevant algorithms and hardware.

"One of the most valuable outcomes of the experiment has been capability building," said Harbour and Milner.

"The experiment created practical learning opportunities for our colleagues, through hands on code reviews, detailed walkthroughs of algorithmic decisions, and the establishment of our Quantum Ambassador Programme, a group responsible for deepening expertise, exploring emerging use cases, and helping to grow a thriving internal quantum community, on code reviews, detailed walkthroughs of algorithmic decisions, and the establishment of our Quantum Ambassador Programme."

FOLLOW US ON SOCIAL MEDIA

Follow ITPro on Google News and add us as a preferred source to keep tabs on all our latest news, analysis, views, and reviews.

You can also follow ITPro on LinkedIn, X, Facebook, and BlueSky.