In partnership with the Financial Conduct Authority (FCA) and Payment Systems Regulator (PSR), Smart Data Foundry has provided synthetic data sets to support a TechSprint focusing on Authorised Push Payment (APP) Fraud.
APP Fraud accounted for 44% of all financial fraud in 2021, overtaking card fraud losses for the first time. £583m was lost due to APP scams in 2021, up 39% YoY, with 96% of cases and 87% of fraud value impacting individuals as opposed to businesses.
APP scams happen when a person or business is tricked into sending money to a fraudster posing as a genuine payee. These types of scams can have a devastating impact on the people who fall victim to them. Fraudsters are particularly adept at praying on the financially vulnerable and maximising the use of faster payments, meaning the money is taken almost instantly, making it practically impossible to tackle the criminals behind the fraud.
The FCA and PSR have joined forces with industry participants to work collaboratively to further understand the technological solutions available in the market, how valuable data could be shared, and possible gaps and barriers.
The three-day TechSprint brought together financial services providers, innovators, academics, regulators, technologists and subject matter experts to collaborate intensively and solve specified problems by building prototype technology solutions.
A critical element of the TechSprint is access to representative and relevant data that brings to life the end-to-end lifecycle of APP fraud. Through agent-based data synthesis Smart Data Foundry has been able to provide a linked set of datasets to support the event comprising; personal data, bank accounts and transactions, telecommunication accounts and text/call records, as well as multiple types of synthetic fraud in the data which covers both the perpetrator and victim.
Smart Data Foundry used its leading-edge Smart Agent Simulation capability to create an agent-based modelling approach to generate the synthetic data set. The approach created synthetic data without commercial or privacy risk, as it was not created by cloning real data. In addition, for the first time, the synthetic data has been able to simulate events such as mobile phone conversations and emails and the associated connection with financial fraud to show the end-to-end story of APP fraud, as told through the eyes of data.
Bryn Coulthard, Chief Platform Officer, commented on the approach Smart Data Foundry took: “Smart Data Foundry focus on creating high utility Synthetic Data providing the ability to understand complex scenarios without exposing customers data”.
Smart Data Foundry’s purpose is to open finance for good by inspiring financial innovation and improving people’s lives by unlocking the power of financial data. One of their core missions focuses on the cost-of-living crisis and how they can ‘stop the squeeze’ for consumers and businesses.
Bryn added, “We’re mission-led, using financial data to help tackle the most pressing issues that face society, the economy and the environment. The work we’re doing with the FCA and PSR helps to shine a light on how consumers and businesses are increasingly struggling to make ends meet, not just because of rising costs but also because of the ever-present risk of being a victim of a scam or fraud.”
Jessica Rusu, Chief Data, Information and Intelligence Officer at the FCA, said, “TechSprints bring together participants from across, and beyond the financial services sector, to develop technology-based ideas or proof of concepts that address and help provide solutions to industry challenges. These events help bring important systemic issues to the forefront, inform our thinking as a regulator, and provide a forum for collaboration and innovation. “
“Using synthetic data helps bring to life the challenges we’re working to fix and lets the TechSprint participants quickly test ideas and show the art of the possible.”
Kate Fitzgerald, Interim Head of Policy at the PSR, said: “The PSR has been working to fight APP scams by driving the adoption of Confirmation of Payee and working with industry to improve data sharing for fraud detection, as well as improving reimbursement for victims via the CRM code. Most recently, we’ve set out our proposals to make reimbursement for victims mandatory.”
“The joint PSR and FCA TechSprint is a great opportunity to build on this important work. It gives us a chance to hear from people from a range of backgrounds, with different skills, to explore solutions to an issue that continues to have a devastating impact on so many. This sprint plays a key role in more accurately illustrating the real-life scams people face and helping us all go further in tackling them.”
Would like to know more - read our relevant articles
Generating Synthetic Data
Smart Data Foundry (Formerly GOFCoE) Data Science team continues to explore and learn techniques for generating synthetic data. They took part in a week-long synthetic data challenge, organised by the High-Level Group for Modernisation of Official Statistics (HLG-MOS) to continue this journey.
Smart Data Foundry data science team wins international synthetic data challenge
Members of our Data Science team were recently invited to enter an international synthetic data challenge under our previous name of the Global Open Finance Centre of Excellence (GOFCoE) organised by the United Nations Economic Commission of Europe (UNECE) High Level Group for Modernisation of Official Statistics (HLG-MOS).
Smart Data Foundry instrumental in FCA tech sprint
A recent collaboration between Smart Data Foundry and the FCA required us to produce bespoke datasets that supported their new Digital Sandbox. Our expertise aided the FCA in building their knowledge of synthetic data, a growing technological product that is predicted to take over the entire AI landscape in as little as five years.