Sumitomo Mitsui Financial Group has conducted a new joint field trial – in collaboration with the Japan Research Institute and Fujitsu – to investigate the effectiveness of an artificial intelligence-based technology to provide automatic recommendations for software repairs.
Through the use of AI, the technology aimed to leverage data from static analysis tools to generate recommendations for bugs in software.
Results revealed the solution “could recommend appropriate repairs for over half of the latent bugs detected” and ultimately can reduce the time required to repair the latent bugs by up to 30% in comparison to manual operations.
In the release, the technology is described: “This technology synthesises repairs based on a set of repair strategies and recommends them to developers. The repair strategies are learned from repair examples of previous latent bugs using AI.
“An AI model is trained on examples of repairing latent bugs extracted from the development history of a wide variety of software projects, deriving repair strategies for different bug types.
“When applied to latent bugs in software under development, this technology uses these learned repair strategies to automatically synthesise and recommend repairs for the bugs, to the developer. “
The trial, led by Fujitsu Laboratories of America and SMFG Silicon Valley Digital Innovation Laboratory, was applied to software for the system that handles financial transactions for Sumitomo Mitsui Banking Corporation (SMBC).
Overall, the trio expect this type of technology to be leveraged in the future as it can dramatically cut short software development and maintenance times as developers will no longer need to repair each latent bug.
