Zempler Bank needed to implement advanced machine learning for fraud detection using Python while maintaining strict banking security standards and governance requirements, but lacked proactive vulnerability screening.
Anaconda Platform provided pre-screened Python packages, vulnerability scanning, and trusted sourcing, enabling secure development and faster production deployment of sophisticated fraud detection models.
Zempler Bank is a pioneering UK digital bank, serving small and medium-sized enterprises (SMEs), sole traders, and consumers. Operating with a full banking license since 2021, this fintech company has built its reputation on delivering secure, efficient banking services to businesses that value simplicity and service. As Head of Data Science at Zempler Bank, James Coveney and his team face developing challenges in detecting fraud with precision while maintaining seamless customer experiences. This challenge has intensified as fraudsters became more sophisticated and the volume of transactions requiring real-time analysis continues to grow.
The team needed to leverage cutting-edge machine learning techniques, but their security and compliance requirements demanded strict governance over code dependencies in production systems. This created a fundamental tension: how to move fast with innovation while maintaining the rigorous security standards banking regulators require.
“With AI getting more complex, having loads of disparate data inputs and making sure that the algorithms we deploy are stable and perform as we expect is a challenge,” explains Coveney, who oversees a team responsible for developing algorithms across areas such as fraud detection, credit risk, and anti-money laundering (AML). “The only way to do that is to use data science. You have to use machine learning to deliver anything that is sufficiently complex.”
Breaking Free from Legacy Statistical Software
Previously, the team was relying on traditional statistical software for their critical modeling work. While their previous platform had served them adequately for building credit scorecards and analytics, it was becoming a significant limitation as they sought to implement more sophisticated machine learning techniques.
“We wanted to start using gradient boosted decision trees, which are very useful in our industry,” Coveney explains. “The support for those kinds of techniques in our previous platform was very limited.”
The proprietary nature of their existing solution meant the team was entirely dependent on the vendor’s development roadmap. “When you use an enterprise, closed-source language, you’re at the behest of the developers of that language,” he notes. “There will be a lot of times when you have to spend a large amount of time doing some bespoke solution, making the code do something that there’s not an inbuilt function for.”
Anaconda’s open source ecosystem offered access to cutting-edge techniques as soon as they became available. “With Python, it’s very unlikely that someone hasn’t solved a problem in a certain way,” Coveney explains. “You get all the benefits of open source: newer things are available very quickly, there’s a huge amount of innovation happening.”
The Security Challenge in Financial Services
However, Zempler Bank used Python sparingly in their production environment due to security concerns. The team needed access to the latest open source packages for more advanced fraud detection models, but their security requirements demanded strict controls over package vulnerabilities.
“What Anaconda gives us is the ability to pre-screen our development environment so that we know that when we release into production there are no vulnerabilities,” Coveney explains. “The problem we had in the past was that our algorithms are, by necessity, developed on production data, so full access to open-source code was not an option within this environment. Similarly, we did not want to leave security-scans to the implementation phase of the development.”
The alternative of manual vulnerability scanning after development created significant bottlenecks and potential security gaps with other open-source software. Without proactive screening, developers would often discover vulnerabilities only after committing code, forcing them to stop their current work and spend days or even weeks retrofitting fixes. “It can be pretty material,” Coveney explains. “If somebody’s used a version of a package that has a vulnerability, and the fix is to upgrade to a version that has material changes, they might have to go and rewrite the entire codebase that they’ve written. It could add a good week or two onto something in the worst case scenario.” Even in simpler cases, the team faced “a fairly regular stream of half-day, one-day fixes,” constant interruptions that pulled analysts away from strategic work.
By catching vulnerabilities proactively rather than reactively, Anaconda’s trusted distribution eliminated these cascading effects of dependency conflicts. “We need all the different code versions to work together.”
“It makes development much more secure for us, and because we have that confidence that what we’re going to release hasn’t got any vulnerabilities, it also removes human error,” Coveney notes. The seamless integration of Anaconda also provided immediate efficiency gains in daily workflows, with improvements that compound across the team’s development work to create meaningful productivity gains over time.
Accelerating Critical Fraud Detection
With Anaconda Platform providing a secure development environment, Zempler Bank’s data science team could focus on building sophisticated fraud detection models that protect both the bank and its customers from financial crime.
Fraud detection in banking requires analyzing vast amounts of disparate data in real-time, including transaction details and customer spending history, behavioral patterns, device information, and session data. The challenge is detecting fraudulent activity among the less than 1% of transactions that are actually fraudulent, while minimizing false positives that would disrupt legitimate customers.
“The only way to do that is to use data science,” Coveney explains. “You need to find that balance between fraud prevention and making the customer experience as smooth as possible, not declining too many legitimate transactions, and not having people sit at checkout ringing their bank to approve purchases.”
The business impact has been remarkable. Using machine learning models built on Anaconda Platform, Zempler Bank has reduced fraud by over 90%, with a limited impact on genuine customers and complaints.
For small businesses, a core part of Zempler Bank’s customer base, this protection is particularly crucial. “Some of the most damaging fraud for small businesses is scams such as invoice redirect or CEO scams as well as account takeover,” Coveney notes. “Small businesses also sometimes have heightened risk of card fraud in instances where they may have multiple cardholders within the company, which increases the risk of the details being compromised.”
Enabling Enterprise-Scale AI Innovation
What sets Anaconda apart for Zempler Bank is its comprehensive approach to the entire AI development lifecycle. Rather than piecing together multiple security tools, they leverage a unified platform that addresses their needs from development through deployment.
“What we get is all the benefits of open source: newer things are available very quickly, there’s a huge amount of innovation happening,” Coveney explains. “Anaconda overlays the most important elements of enterprise security onto an open-source language, which means you retain access to cutting-edge tools while bringing in the security and governance elements that we need as a bank.”
For financial crime detection, where the team might need to implement new algorithms or retrain existing models quickly in response to emerging threats, this streamlined workflow is essential. “You do sometimes need to react quite quickly. You might want to implement a new algorithm or retrain an existing one and get it into production as quickly as you can,” Coveney notes. “That can only be done if you make the process as simple as possible.”
Expanding AI Across the Organization
The success with fraud detection has opened doors for broader AI initiatives across Zempler Bank. The team is now using Anaconda across all their data science projects, with more key initiatives across credit, customer experience, and marketing.
“We have been able to use more advanced ML in areas such as credit, customer experience, and marketing where before we were limited in what we could automate,” Coveney explains.
The Governance Advantage
For Zempler Bank’s security team, Anaconda provided exactly what they needed: a trusted solution that removed human error from the security equation while enabling innovation.
“Our CISO was involved in the sign-off process,” Coveney recalls. “They were thrilled when I suggested it as a tool, because otherwise it would have been something we’d have to build manually. We would have had to basically do what Anaconda has done ourselves, which wouldn’t have been a valuable use of time.”
With Anaconda’s governance framework in place, the organization gained the visibility and control needed to satisfy audit requirements while empowering the data science team to innovate at speed. This eliminated the traditional tension between security and agility.
Looking Forward: The AI-First Future
As Zempler Bank continues to expand their AI capabilities, they’re positioned to unlock even greater efficiencies with Anaconda as their foundation. The team’s roadmap includes further enhancement of underwriting processes and continued expansion of machine learning applications across customer-facing and operational systems.
“The most important part of the process is how you are bringing AI/ML into production in a secure, efficient, and scalable manner,” Coveney reflects. “Anaconda has been very important in allowing us to ensure we have security embedded into our code from the onset of a project, making the transition to production much smoother.”
His advice to other data science leaders emphasizes minimizing the gap between development and production environments: “I would recommend ensuring that the tools you use in development of ML/AI are as closely aligned to those you use to bring it into production as possible, in order to minimize the amount of re-coding involved in implementation. The smaller the gap between these two environments, the faster the implementation and the lower the chance of models being implemented incorrectly.”
For Zempler Bank, Anaconda Platform has delivered exactly what they needed: the confidence to innovate with open source at enterprise scale, backed by the security and governance their business requires. From protecting customers against sophisticated fraud schemes to enabling rapid deployment of new AI capabilities, Anaconda has become the foundation for their data-driven transformation.
Ready to accelerate your AI initiatives with trusted open source? Discover how the Anaconda Platform can transform your data science workflows while maintaining enterprise-grade security and governance. Contact our team for a personalized demonstration.
Anaconda Platform
The Only Unified Platform for Open Source