Our extensive industrial collaboration enables us to do research with immediate application to software development practices in realistic settings.
Our paper "Variability-Aware Performance Prediction: A Statistical Learning Approach" accepted at ASE 2013
Our paper "Variability-Aware Performance Prediction: A Statistical Learning Approach" has been accepted as a full paper (acceptance rate: 51/317 ≈ 16%) at the 28th IEEE/ACM International Conference on Automated Software Engineering (ASE 2013). This paper proposes a variability-aware approach via statistical learning to predict a configuration’s performance based on small random samples. The corresponding, ongoing project can be found here.