Mizuho and IBM test Gen AI for IT incident response management

When a disruption occurs, banking systems must be restored quickly and accurately. However, once an error is detected, operators often receive a flood of messages and reports, making it difficult to determine the cause of the event and ultimately delaying recovery time.

The new solution was tested as a proof of concept and demonstrated 98% accuracy in monitoring and responding to error messages during a three-month test.

The PoC added patterns likely to cause incident response errors to generative AI and linked an application that supports a series of operations in event detection to IBM’s Watsonx supercomputer to shorten recovery steps and improve recovery speed.

By leveraging Watsonx, Mizuho has also been able to simplify internal operations and enable flexible configuration of monitoring and operations menus by on-site personnel when higher levels of security and confidentiality are required.

Mizuho and IBM say they plan to expand the event detection and response PoC and apply it to production environments in the coming year.

Mizuho is a passionate advocate of the use of generative AI. The Japanese bank is working with Fujitsu to apply generative AI technologies to work processes and tasks, including source code generation, system development and maintenance.

In June last year, the bank went a step further and integrated the technology company-wide by making Microsoft’s OpenAI platform available to its 45,000 employees.