SIX, the organisation responsible for running the financial-market infrastructure of Switzerland and Spain, is turning to synthetic data to address one of the most persistent challenges in modern banking technology: the difficulty of accessing realistic datasets for software testing, model development and analytics without breaching strict privacy and compliance rules.
As a global provider of transaction-security services, financial-information processing, payment clearing and digital-infrastructure capabilities, SIX manages enormous amounts of sensitive financial data on behalf of more than 120 national and international financial institutions, including Barclays, Bank of America and most major Swiss and international banks.
Its recent work with synthetic data shows how financial-sector QA teams can safely unlock the value of production-like datasets without exposing customer information.
The report highlights that SIX’s data scientists struggle to access original, up-to-date datasets because regulations, privacy restrictions and siloed systems prevent free internal use and sharing.
Data is distributed across multiple business units, making it difficult to assemble a complete picture, and many analyses are still performed locally rather than in the cloud, further limiting performance and scalability.
These barriers slow the delivery of insights, delay development and testing cycles, and reduce the organisation’s ability to collaborate effectively across teams.
For QA teams, the impact is familiar: limited access to representative test data, long provisioning times and challenges in validating digital services at the speed required by modern development.
Synthetic data as a compliance-safe alternative for testing
To overcome these constraints, SIX partnered with Syntheticus, a platform that generates artificial yet statistically faithful datasets using generative-AI techniques and differential-privacy safeguards.
Synthetic data, as described in the report, mimics the original data while removing all personally identifiable information. Because it no longer contains any real customer details, the synthetic version is not treated as personal data under GDPR and can be shared, analysed and stored much more freely. This opens the door to cloud-based testing, secure collaboration with external partners and faster development cycles across the organisation.
The Syntheticus platform processes original datasets and applies machine-learning algorithms to synthesise, secure, validate, augment and enrich the data.
The output is a synthetic dataset that behaves like the real one in terms of distributions, correlations and patterns, but without carrying any privacy risk. This allows engineering, QA and analytics teams to populate test environments, build models, validate new systems and run scenario-based tests without needing to request masked data or wait for compliance approval.
Also, it supports the development of fraud-detection models, risk-scoring tools and customer-behaviour analyses, all of which require rich historical data that cannot normally be shared internally in raw form.
Proof of concept
A Proof of Concept was carried out using a loan-default-risk dataset containing 100,000 rows and 11 columns of sensitive customer information. Because the dataset included names, addresses and bank-account numbers, it could not be shared outside controlled environments.
For the POC, the dataset was truncated to 5,000 rows and used to generate a synthetic version of equal size and structure. The evaluation compared the utility of the synthetic data against the original using standard classification algorithms and multiple statistical metrics.
The synthetic dataset achieved strong alignment with the real dataset, preserving statistical structure and modelling performance. Privacy evaluation confirmed that no synthetic record duplicated any real record and that each synthetic entry maintained sufficient distance from its closest real counterpart, ensuring that no customer information was reproduced or inferred.
The results showed that synthetic data allowed SIX’s analytics teams to run predictive models, testing tasks and advanced analyses with consistent results while remaining fully compliant with privacy regulations.
The use of synthetic data sped up development cycles, enabled secure use of cloud infrastructure, increased scalability and improved overall data literacy within the organisation.
By eliminating delays caused by traditional data-provisioning processes, synthetic data also reduced administrative burdens and increased the organisation’s ability to make data-driven decisions.
For QA and software-testing teams across the financial sector, SIX’s experience offers a clear message. As banks face growing regulatory pressure, rising data-security expectations and increasing reliance on cloud-native development, synthetic data provides a practical path forward.
It delivers the realism needed for robust testing and model validation without exposing institutions to privacy or compliance risk. In doing so, it is becoming a foundational enabler of faster, safer and more innovative digital-product delivery across banking and financial services.
Why not become a QA Financial subscriber?
It’s entirely FREE
* Receive our weekly newsletter every Wednesday * Get priority invitations to our Forum events *
REGULATION & COMPLIANCE
Looking for more news on regulations and compliance requirements driving developments in software quality engineering at financial firms? Visit our dedicated Regulation & Compliance page here.
READ MORE
- Inside JPMorgan’s $18bn QA push with OmniAI reshaping testing
- As AI takes hold, insurance firms face a new testing mandate
- K2view’s Amitai Richman calls out the ‘real bottleneck’ in healthcare and insurance
- AI in QA: how flexible testing is redefining assurance for financial firms
- Explainer: Why site reliability engineering is gaining momentum in banking
WATCH NOW
QA FINANCIAL PODCASTS
Listen to Sudeepta Guchhait on Nasdaq’s new Mimic AI testing platform
QA Financial sits down with Sudeepta Guchhait, Senior Director of Product Framework & Quality Engineering at Nasdaq
——–
Listen to Wesley Scheffel and Robin Rain on Schroders’ DevOps strategy
We catch up with Wesley Scheffel, Head of Cloud Platform and Product Engineering at Schroders, and Robin Rain, Head of Cloud Platform Architecture
——–
Listen to Citi’s Jason Morris on Lightspeed and the future of continuous delivery
Jason Morris, Head of Developer Pipelines for Securities Markets and Banking at Citi, talks about Lightspeed
