A comparative analysis of the efficiency of change metrics and static code attributes for defect prediction

By Raimund Moser, Witold Pedrycz, Giancarlo Succi. 2008 ACM/IEEE 30th International Conference on Software Engineering, 2008

771 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/71430a83159235b456b2e50d0e847aefc7cc46e8

How researchers see this paper

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

In Computer Networks and Communications

In Information Systems

In Software

Citations in the corpus

Software fault prediction metrics: A systematic literature review (2013, neutral): “The study is concluded in Section 5.”
Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models (2015, background): “, Chidamber and Kemerer (CK) metrics [9]), process metrics [3, 24, 40, 42] (e.”
The road ahead for Mining Software Repositories (2008, neutral): “for the Eclipse open source project [52].”
The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models (2018, neutral): “First, defect prediction models can be used to predict modules that are likely to be defect-prone in the future [1], [2], [3], [4], [5], [6], [7], [8], [9].”
A systematic review of machine learning techniques for software fault prediction (2015, background): “Hence, total number of 122 studies [1, 2, 20-139] were identified for further processing and analysis.”
Evaluating defect prediction approaches: a benchmark and an extensive comparison (2011, methodology): “MOSER We use the catalog of file-level process metrics introduced by Moser et al. (2008) listed in Table 2.”
Dealing with noise in defect prediction (2011, methodology): “Since most automatic buggy change/file identifications are based on special keywords and links [11, 16, 28, 33, 36] in the change logs, this will lead to false negatives (missing some buggy changes) in the automatically identified data.”
On the "Naturalness" of Buggy Code (2015, background): “survey and provide a direct comparison of a number of representative DP approaches (including those using process metrics, such as previous changes [34, 17] and defects [27], and product metrics, such as code complexity metrics [6]).”
Learning to rank relevant files for bug reports using domain knowledge (2014, background): “Moser et al. [30] and Kim et al. [20] use machine learning techniques to train a prediction model based on code changes.”
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.”
Software Defect Prediction via Convolutional Neural Network (2017, background): “Software defect prediction [4], [5], [6], [7], [8] is a process of building classiﬁers to predict code areas that potentially contain defects, using information such as code complexity and change history.”
A large-scale empirical study of just-in-time quality assurance (2013, methodology): “Other work uses process metrics to predict defect-prone locations [15], [19], [43], [44], [46].”
Fair and balanced?: bias in bug-fix datasets (2009, neutral): “The Eclipse dataset 2 is well-documented and has been widely used in research [13] [49] [36] as well as in the MSR Conferences' mining challenges in the years 2007 and 2008.”
Automatically Learning Semantic Features for Defect Prediction (2016, methodology): “Software defect prediction techniques [12,18,20,23,27,32, 38, 40, 52, 62, 70] have been proposed to detect defects and reduce software development costs.”
On the relative value of cross-company and within-company data for defect prediction (2009, background): “” Easy to collect: Employing defect predictors in practice should not take too much time (Moser et al. 2008) for data collection and constructing the models themselves.”
An extensive comparison of bug prediction approaches (2010, background): “We minimized this threat by using parts of Eclipse in our benchmark, a system that while being open-source has a strong industrial background.”
Predicting faults using the complexity of code changes (2009, background): “[25], show that process metrics outperform code metrics as predictors of future faults.”
Transfer defect learning (2013, methodology): “Index Terms—cross-project defect prediction, transfer learning, empirical software engineering I. INTRODUCTION Recently, numerous effective software defect prediction approaches have been proposed and received a tremendous amount of attention [1], [2], [3], [4], [5].”
How, and why, process metrics are better (2013, background): “[18] compared the prediction performance of code and process metrics in three releases of Eclipse and found that process metrics may outperform code metrics in defect prediction.”