Machine Learning Methods are growing in popularity in every aspect of research and industry including Software Engineering. With this group, we aim to merge current state-of-the-art practices in both areas to create new ways with which to develop and improve code.
Most of our solutions are implemented as either part of JetBrains IDE or as standalone plugins.
Main research projects
- Creating a metrics-based method for architecture defects detection in object-oriented code and automatic creation of appropriate refactorings that optimize code structure.
- API-based code generation based on the Bayou project.
- Anomaly detection for programs in Kotlin.
- User intent and context analysis for smarter autocompletion and documentation suggestions.
- Commit-based analysis of code repositories predicting methods to change, bugs location and other events.
- Analysis of code structure and style for plagiarism detection, finding programmers with similar code styles etc.
- Data-driven systems for code auto-patching