Is the commit buggy?

Identifying defective code (bugs) in commits from a software repository may improve productivity and reduce the amount of corrections that need to be applied in production. We present a framework based on deep learning that could help identify buggy commits. The algorithms are trained on a well-known cloud infrastructure management code repository

• Deep learning could be used for identifying buggy commits
• Accuracy of identification differs depending on the approach
• Open source dataset and example code are available to facilitate reproduction and building applications around the framework

————————————————————————————————————————————————————

Catalin Meirosu – Head of Systems Management 1 | Ericsson, Product Development Group Software-Defined Infrastructure

Catalin is a results-oriented leader with over 13 years of experience at Ericsson. His work focuses on making telecommunication networks self-managing. He lead a team that focused on analytics and open-source contributions while successfully incubating the Cloud RAN product. Currently he leads the Systems Management team that is responsible for the architecture and technical evolution of the Software-Defined Infrastructure products at Ericsson.

Abgeiba Yaroslava Isunza Navarro – Machine Learning Engineer | Modulai AB

Abgeiba is a machine learning engineer at Modulai. She has ML experience in NLP, finance and healthcare. Prior to joining Modulai she worked in ML projects at Ericsson and BBVA banking. Abgeiba holds a M.Sc. in Machine Learning from KTH Royal Institute of Technology, Stockholm and a B.Sc. in Telecommunications and Electronics from Tecnológico de Monterrey, Mexico. Outside of work she enjoys travelling, painting and learning new languages