Prasad Kawthekar
Papers
1
Total Citations
86
H-Index
1
About
Prasad Kawthekar is a researcher whose work sits at the intersection of software engineering and machine learning, with a particular focus on improving the performance and adaptability of highly configurable software systems. His most cited work, "Transfer Learning for Improving Model Predictions in Highly Configurable Software" (2017, 86 citations), addresses a critical challenge in modern software engineering: how to efficiently predict system performance across a vast configuration space. Kawthekar pioneered the application of transfer learning techniques to this domain, enabling models trained on limited configuration data to generalize effectively to unseen environments. This approach significantly reduces the cost and effort of performance modeling in self-adaptive systems, where software must dynamically adjust to changing conditions. His contributions have been influential in the field of software performance engineering, providing a practical bridge between machine learning and configurable system optimization. Kawthekar's work continues to inform research on automated software adaptation, demonstrating how intelligent reuse of learned knowledge can make complex, configurable systems more predictable and efficient.
Research Focus
Key Achievements
Top Papers
- 1