Titre : Using ML to predict, prevent and fix bugs at Ubisoft

Conférencier : Dr. Mathieu Nayrolles

Résumé :
Preventing defects to reach consumers is one of the most important tasks of any application developer. Using machine learning and pattern matching, we attempt to automatically prevent defects from reaching the central code repository by intercepting them at commit-time. In this talk, we present an approach to detect and resolve, defects in large polyglot projects. Our approach, when evaluated on past contributions, was able to detect ~65% of the commits containing defects. In addition, this project allowed us to improve our coding practices by discovering new guidelines that apply to our application domain, in our case high-budget game development.

Bio :
Dr. Mathieu Nayrolles has ten years of experience in software quality and productivity. He obtained an M.Ing Soft. Eng. from CESI (France), an MS.c Comp. Sci. from UQAM and a Ph.D. ECE from the Intelligent System Logging and Monitoring lab (Concordia, Montréal, Canada) in 2018. He's now a Technical Architect at Ubisoft Montreal where he leads a team of engineers that focuses on improving the productivity of the thousands of Ubisoft developers scattered around the world. He presented at various international conferences such as SANER, MSR, WCRE or CPPCON. He also wrote six books on open-source technologies such as Angular, Solr or Magento.

Bienvenue à tous!