Scaling a Core Banking Engine Using Apache Kafka

Core banking is one of the last bastions for the mainframe. As many other industries have moved to the cloud, why are most of the world’s banks yet to follow? The answer lies in a bank's conflicting needs: correctness and scale - historically achievable using a monolithic application running on a large mainframe. The clock is ticking for the banks as we approach an inflection point where the mainframes become too expensive, and aren’t flexible enough to meet the modern banking consumers needs A simple lift and shift onto the cloud does not work. As we distribute our core processing we spend an increasing amount of time on the network, and race conditions lurk that threaten ‘correctness’ This session explores how Thought Machine’s core banking system ‘Vault’ was built in a cloud first manner, leveraging Kafka to enable asynchronous and parallel processing at scale, specifically focusing on the architectural patterns we have used to ensure ‘correctness’ in such an environment.

Peter Dudbridge
Director of Engineering, Thought Machine