Mizuho and IBM have collaborated to develop a proof of concept (PoC) system that utilizes watsonx, IBM’s enterprise generative AI and data platform, to enhance the efficiency and accuracy of Mizuho’s event detection operations.
During a three-month trial, the new solution demonstrated a 98% accuracy in monitoring and responding to error messages, says IBM. The companies plan to continue expanding and validating the system in the future.
Banking systems require accurate and early recovery when disruptions occur. However, when an error is detected, operators often face a flood of messages and reports, making it challenging to identify the root cause of the event and prolonging the recovery time. To tackle this issue, the companies conducted a PoC aimed at improving the efficiency of error detection using watsonx, says IBM.
The PoC involved adding patterns likely to cause errors in incident response to generative AI and linking an application supporting a series of operations in event detection with watsonx.
Mizuho and IBM intend to expand the event detection and response PoC and apply it to production environments within the next year. The companies also plan to work on incident management and advanced failure analysis using generative AI.
[Image courtesy: Mizuho]