Mizuho Financial Group, Inc. and IBM collaborated on the development of a proof of concept (PoC) using watsonx, IBM’s enterprise generative AI and data platform, to improve the efficiency and accuracy of Mizuho’s event detection operations.
The new solution demonstrated a 98% accuracy in monitoring and responding to error messages during a three-month trial. Mizuho and IBM aim to continue expanding and validating the system in the future.
When a disruption occurs, banking systems require accurate and early recovery. However, when an error is detected, operators often receive an influx of messages and reports, making it difficult to pinpoint the cause of the event, and ultimately delaying the recovery time.
Also Read: Insight Works with Microsoft, Qualcomm as Early Provider of Next-Generation AI PCs
To address the issue, Mizuho and IBM conducted a PoC for improving the efficiency of error detection, utilizing watsonx.
The PoC added patterns likely to cause errors in incident response to generative AI and linked an application supporting a series of operations in event detection with watsonx, helping to shorten the steps to recovery and improve recovery speed.
Utilizing watsonx also enabled Mizuho to facilitate in-house operations and allow for the flexible configuration of monitoring and operation menus by on-site personnel when higher levels of security and confidentiality are required.
Mizuho and IBM plan to expand the event detection and response PoC and apply it to production environments in the coming year. Mizuho and IBM also plan to work on incident management and advanced failure analysis using generative AI to further improve the efficiency and sophistication of operations.
Source: IBM
