SUEMATSU-Yasuharu Award

Research and Development of a Just-In-Time Bug Prediction Model to Support the Continuous Evolution of OSS Development Projects

Contribution to academia

Yasutaka KAMEI
Yasutaka KAMEI

Yasutaka Kamei received his B.S. degree in informatics from Kansai University, Osaka, Japan, in 2005 and M.E. and D.E. degrees in information science from Nara Institute of Science and Technology, Nara, Japan, in 2007 and 2009, respectively. From 2008 to 2010, he was a Research Fellow of the Japan Society for the Promotion of Science. From 2010 to 2011, he was a Postdoctoral Fellow at Queen’s University, Ontario, Canada.

From 2011, he was an Assistant Professor with the Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan and was subsequently promoted to Associate Professor of that university in 2015.

In recent years, the environment surrounding open source software (OSS) has been changing dramatically. The existence of OSS has become more familiar to end users, and vendor companies have come to recognize that the value of OSS is not confined to mere cost reduction but also plays a key role in the introduction of the latest technology. In order to support the continuous evolution of OSS, a framework that automatically detects and notifies OSS developers of bugs in the source code is required to ensure reliability and improve development efficiency as bugs can be the source of program malfunctions and vulnerabilities.

Yasutaka Kamei has played a major role in the Mining Software Repositories (MSR) research field, which advocates evidence-based recovery and modelling of software quality by analyzing large-scale software development datasets. One of his notable research achievements is the development of a Just-In-Time bug prediction model that automatically identifies risky software changes by analyzing the development activities in real time. It has been said that there are various technical issues to be solved to realize fine-grained (per code change) and real-time prediction, such as building a prediction model with limited information. He has solved these problems by using techniques that are applicable to a wide range of software development projects, such as integration of multiple software repositories, discovery of similar projects, and utilization of context, to achieve just-in-time bug prediction.

Hence, we believe that his outstanding contributions to the fields of electronics, information, and communication make him a worthy recipient of this prestigious award. We are also convinced that he will continue making significant contributions to scientific and technological progress.