Defect prediction from static code features: current results, limitations, new approaches

By Tim Menzies, Zach Milton, Burak Turhan, Bojan Cukic, Yue Jiang, Ayse Basar Bener. International Conference on Automated Software Engineering, 2010

470 citations recorded by the source corpus.

Subfields: Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/0600fc43809517453db4744f77895d728d2ed825

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Software

Citations in the corpus

A large-scale empirical study of just-in-time quality assurance (2013, background): “Menzies et al. [36] commented on the fact that there are many industrial situations where low-precision and high-recall prediction models are still extremely useful when the data are imbalanced.”
Evaluating defect prediction approaches: a benchmark and an extensive comparison (2011, background): “Previous studies that advocated the absence of stability in the domains of effort estimation (Foss et al. 2003; Myrtveit et al. 2005) and defect prediction ( Menzies et al. 2007 ) are still unchallenged.”
Software Defect Prediction via Convolutional Neural Network (2017, methodology): “Therefore, software defect prediction techniques which automatically find potential bugs have been widely employed to help developers allocate their limited resources [3].”
Deep Learning for Just-in-Time Defect Prediction (2015, methodology): “Much research has been done on defect prediction; these techniques construct predictive classification models built on features such as lines of code, code complexity and number of modified files [2], [3], [4].”
The impact of tangled code changes (2013, background): “Such mined information can be used to predict related changes [1], to predict future defects [2], [3], to analyze who should be assigned a particular task [4], [5], or to gain insights about specific projects [6].”
Online Defect Prediction for Imbalanced Data (2015, background): “…Tan Sashank Dara Caleb Mayeux University of Waterloo, Canada University of Waterloo, Canada Cisco Systems, India Cisco Systems, USA m9tan@uwaterloo.ca lintan@uwaterloo.ca sadara@cisco.com cmayeux@cisco.com Abstract Many defect prediction techniques are proposed to improve software reliability.”
Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models (2015, background): “Despite recent advances in machine learning, studies suggest that the classification technique used to train defect prediction models has little impact on its performance [34, 38, 56].”
An investigation on the feasibility of cross-project defect prediction (2011, methodology): “We employed 5 machine learning algorithms to 2 Previous studies of Menzies et al. (2008, 2010) show that defect predictors hit “performance ceiling”, some inherently higher bounds of performance that cannot be break through by simply adopting different learning algorithms.”
A Systematic Literature Review on Fault Prediction Performance in Software Engineering (2012, unknown): “For example, Menzies et al. [[113]] say that severity is too vague to reliably investigate, Nikora and Munson [[126]] says that “without a widely agreed deﬁnition of severity we cannot reason about it” and Ostrand et al. [[133]] state that severity levels are highly subjective and can be inaccurate…”
An empirical study on software defect prediction with a simplified metric set (2014, methodology): “s achieved many useful conclusions. Currently, some improved classiﬁers [26, 54, 65] and hybrid classiﬁers [30, 31] have also been proposed to eectively improve classiﬁcation results. Menzies et al. [33] advocated that dierent classiﬁers have indiscriminate usage and must be chosen and customized fo”