We all have heard of the amazing things Machine Learning can do. It can drive cars, it can detect whether people are using safe equipments, it can play games. But… can it help software developers in, say, find bugs or refactor code?

In this talk, I’ll go through the different research projects I was involved in the area. I’ll show that machine learning models can, in fact, learn a lot about how we develop software, and recommend interesting things to developers. In particular, I’ll talk about models that recommend refactoring (done together with ING), models that find bugs and models that recommend which methods to log (both done together with Adyen).

You don’t need to be an expert in machine learning to follow this talk.

Slides

Link to slideshare: https://www.slideshare.net/mauricioaniche/can-ml-help-software-developers-teqnation-2022

Video (in english)

Video (in pt-br)

Presentations

  • TEQnation 2022
  • ThoughtWorks
  • Zühlke
  • University of California, Davis
  • Universidade Federal do Ceará, campus Quixadá
  • Lambda3
  • RunaHR

References

  • https://www.mauricioaniche.com/publications/log-placement-recommendation/
  • https://www.mauricioaniche.com/publications/learning-off-by-one-mistakes/
  • https://www.mauricioaniche.com/publications/search-based-remodularization/
  • https://www.mauricioaniche.com/publications/ml-and-refactoring/
  • https://www.mauricioaniche.com/publications/anomaly-detection-cps/
  • https://www.mauricioaniche.com/publications/evosql/
  • https://www.mauricioaniche.com/publications/passive-learning-applied/