Advanced Static Analysis for Predicting Performance Bugs (2nd Offering)
Presenter: Younes Jahandideh
Date: Friday, November 21st, 2025
Time: 2:00 pm
Location: Workshop Space, 4th Floor - 300 Ouellette Ave., School of Computer Science, Advanced Computing Hub
This advanced workshop continues from the previous session on static analysis. It explains how new research uses data from code and past project changes to predict where performance problems may appear. Participants will learn how static analysis and simple machine learning methods can be combined to identify slow or inefficient parts of software before they cause issues. Real-world examples from open-source projects demonstrate how these ideas enhance the accuracy and utility of performance predictions for developers.
- Quick Recap: What static analysis and performance bugs are
- Going Deeper: How static tools understand code structure and logic
- Smart Features: What kind of code information helps us predict slowdowns
- Static + Dynamic Data: How combining code analysis with runtime data improves results
- Machine Learning Use: How models like Random Forest or XGBoost learn from code data
- Testing the Predictions: Checking how well our model works and how to improve it
- Modern Challenges: What makes predicting performance bugs hard in real projects
Basic understanding of programming, software engineering, and machine learning.
Younes is a Ph.D. student and research assistant who began his program at the School of Computer Science in Fall 2023. His primary research focuses on learning-based optimization, a type of self-optimizing system in cloud computing.