Faculty

Science

Supervisor Name

Konstantinos Kontogiannis

Keywords

machine learning, git commits, github, software testing

Description

Large software systems are implemented using many different programming languages and scripts, and consequently the dependencies between their components are very complex. It is therefore difficult to extract and understand these dependencies by solely analyzing the source code, so that failure risks can be detected accurately. On the other hand, it is a common practice for software engineers to keep track of process related metrics such as the number of times a component was maintained, with which other components it has been co-committed, whether the maintenance activity was a bug-fixing activity, and how many lines of source code have been altered. These data provide valuable information to be used for training a machine learning model and for devising metrics which can predict the risk associated with a future failure of a component due to maintenance activities in this or in another component related to it.

Acknowledgements

Konstantinos Kontogiannis, Marios Grigoriou, Alberto Giammaria (IBM US, Austin TX. Lab), Chris Brealey (IBM Canada, Toronto Canada Lab)

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Document Type

Poster

Share

COinS
 

Evaluating Machine Learning Model Stability for Software Bug Prediction

Large software systems are implemented using many different programming languages and scripts, and consequently the dependencies between their components are very complex. It is therefore difficult to extract and understand these dependencies by solely analyzing the source code, so that failure risks can be detected accurately. On the other hand, it is a common practice for software engineers to keep track of process related metrics such as the number of times a component was maintained, with which other components it has been co-committed, whether the maintenance activity was a bug-fixing activity, and how many lines of source code have been altered. These data provide valuable information to be used for training a machine learning model and for devising metrics which can predict the risk associated with a future failure of a component due to maintenance activities in this or in another component related to it.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.