Feature-oriented defect prediction

Abstract

Software errors are a major nuisance in software development and can lead not only to reputation damages, but also to considerable financial losses for companies. Therefore, numerous techniques for predicting software defects, largely based on machine learning methods, have been developed over the past decades. These techniques usually rely on code and process metrics in order to predict defects at the granularity of typical software assets, such as subsystems, components, and files. In this paper, we present the first systematic investigation of feature-oriented defect prediction: the prediction of defects at the granularity of features-domainoriented entities abstractly representing (and often cross-cutting) typical software assets. Feature-oriented prediction can be beneficial, since: (i) particular features might be more error-prone than others, (ii) characteristics of features known as defective might be useful to predict other error-prone features, (iii) feature-specific code might be especially prone to faults arising from feature interactions. We present a dataset derived from 12 software projects and introduce two metric sets for feature-oriented defect prediction. We evaluated seven machine learning classifiers with three different attribute sets each, using our two new metric sets as well as an existing metric set from the literature. We observe precision and recall values of around 85% and better robustness when more diverse metrics sets with richer feature information are used. CCS CONCEPTS• Software and its engineering → Software product lines; Software defect analysis; • Computing methodologies → Supervised learning by classification.

Seamless Variability Management with the Virtual Platform

“…First, our calculation of C miss could be incomplete: there might be potential omissions not fixed by a later commit. This situation is comparable to other research that relies on potentially imperfect datasets (e.g., in software defect prediction [67], [68]). While our analysis focuses on omissions that later required fixing, these omissions are arguably the most relevant ones in practice.…”

VaryMinions: leveraging RNNs to identify variants in variability-intensive systems’ logs

“…If some of these works also target classification tasks, they consider configurations as the main entry point of their approaches and do not take into account the behaviour of the studied systems. ML also supports usability prediction Vyas et al (2019), attacks and vulnerabilities detection Abdelrazek et al (2019) and defect prediction Strüder et al (2020); Amand et al (2019). In particular, Strüder et al demonstrated that artificial neural networks were suitable for this last task Strüder et al (2020).…”

A fine-grained data set and analysis of tangling in bug fixing commits

“…We focus the discussion of the related work on the manual untangling of commits. Other aspects, such as automated untangling algorithms (e.g., Kreutzer et al 2016;Pârtachi et al 2020), the separation of concerns into multiple commits (e.g., Arima et al 2018;Yamashita et al 2020), the tangling of features with each other (Strüder et al 2020), the identification of bug fixing or inducing commits (e.g., Rodríguez-Pérez et al 2020), or the characterization of commits in general (e.g., Hindle et al 2008), are out of scope.…”