Data Mining Static Code Attributes to Learn Defect Predictors

By Tim Menzies, Jeremy Greenwald, Art Frank. IEEE Transactions on Software Engineering, 2007

1,526 citations recorded by the source corpus.

Subfields: Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/b9e2ece2c688dd6d491598edefea4236e84ab33d

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

Software defect prediction using ensemble learning on selected features (2015, methodology): “Decision trees [10,11], Bayesian methods [12], and ANNs [14] have paved the way for machine learning-based methods in the field of defect classification.”
Evaluating Complexity, Code Churn, and Developer Activity Metrics as Indicators of Software Vulnerabilities (2011, methodology): “Compared to a random selection of files for inspection and testing, these models would have reduced the number of files and the number of lines of code to inspect or test by over 71% and 28%, respectively, for both projects.”
An investigation on the feasibility of cross-project defect prediction (2011, methodology): “Actually the effectiveness of static code metrics has been debated widely (Menzies et al. 2007b; Turhan et al. 2009; Fenton and Ohlsson 2000; Shepped and Ince 1994).”
Defect prediction from static code features: current results, limitations, new approaches (2010, methodology): “In 2006 (Menzies et al. 2007b), we defined a repeatable defect prediction experiment which, we hoped, others could improve upon.”
A systematic review of software fault prediction studies (2009, methodology): “Many researchers used different approaches such as genetic programming (Evett, Khoshgoftaar, Chien, & Allen, 1998), neural networks (Thwin & Quah, 2003), case-based reasoning (El Emam, Benlarbi, Goel, & Rai, 2001), fuzzy logic (Yuan, Khoshgoftaar, Allen, & Ganesan, 2000), Dempster–Shafer networks (G”
A systematic review of machine learning techniques for software fault prediction (2015, methodology): “[31]) advocate the use of AUC as performance measure for construction of SFP models.”
Transfer defect learning (2013, methodology): “In this paper, we apply a state-of-the-art transfer learning approach, TCA, to make feature distributions in source and target projects similar.”
Software fault prediction metrics: A systematic literature review (2013, methodology): “Halstead [24] N1 Total number of operators [116,88,101,112,111,108,113,148,96,134,142,124]”
Data Quality: Some Comments on the NASA Software Defect Datasets (2013, methodology): “Pre-processing Study Year Version Missing Inconsistent Duplicate items items cases Menzies, Greenwald and Frank [16] 2007 Promise × × × Zhang and Zhang [21] 2007 n.”
Software fault prediction: A literature review and current trends (2011, methodology): “A panel at IEEE Metrics 2002 conference did not support Fagan’s claim that inspections can find 95% of defects before testing and this detection ratio was around 60% (Menzies et al., 2007a).”
Cross-project defect prediction: a large scale experiment on data vs. domain vs. process (2009, background): “There is an extensive body of knowledge on the metrics discussed above when used for predicting quality [12, 13, 19, 22, 28, 29].”
A General Software Defect-Proneness Prediction Framework (2011, methodology): “From our experimental results, we also observe that the predictions of Menzies et al. on the AR data are much more biased than that on the NASA data and the performance of the MGF framework varies greatly with data from different resources.”
Searching for rules to detect defective modules: A subgroup discovery approach (2012, methodology): “[40], the NASA repository can be generalised to the industry in general.”
An Empirical Comparison of Model Validation Techniques for Defect Prediction Models (2017, methodology): “Index Terms—Defect prediction models, model validation techniques, bootstrap validation, cross validation, holdout validation Ç”
Automated severity assessment of software defect reports (2008, background): “Much prior work has used standard data miners, to learn software defect recognizers from historical records of static code features [11].”
How, and why, process metrics are better (2013, methodology): “The value of code metrics in defect prediction has been well-explored [12, 16, 29].”