Miguel Velez

Carnegie Mellon University

Papers

1

Total Citations

86

H-Index

1

About

Miguel Velez is a leading researcher in software engineering, with a focus on highly configurable and self-adaptive systems. His work addresses the critical challenge of predicting software performance under dynamic conditions, where configuration options multiply exponentially. Velez’s most influential contribution, "Transfer Learning for Improving Model Predictions in Highly Configurable Software" (2017, 86 citations), pioneers the use of transfer learning to overcome the prohibitive cost of sampling and modeling every possible configuration. By leveraging knowledge from related environments, his approach dramatically improves prediction accuracy while reducing data requirements—a breakthrough for systems that must adapt in real time. This work has shaped how researchers and practitioners handle performance modeling in complex, evolving software ecosystems. Velez’s research sits at the intersection of machine learning and software engineering, offering practical solutions for self-adaptation, performance optimization, and configuration management. His contributions are widely cited and have influenced subsequent work on efficient sampling, model reuse, and adaptive system design. For students and researchers, Velez’s work demonstrates how cross-disciplinary techniques can solve fundamental software engineering problems, making systems more reliable and efficient in unpredictable environments.

Research Focus

Key Achievements

1
H-Index
1
Papers
86
Total Citations
86
Avg Citations/Paper
🏆 Most Cited Paper
Transfer Learning for Improving Model Predictions in Highly Configurable Software
86 citations · 2017
📈 Most Prolific Year: 2017 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: Carnegie Mellon University

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago