A Systematic Literature Review on Fault Prediction Performance in Software Engineering

By Tracy Hall, Sarah Beecham, David Bowes, David Gray, S. Counsell. IEEE Transactions on Software Engineering, 2012

1,099 citations recorded by the source corpus.

Subfields: Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/eb2640199a8bf20b85b54757a99e07942b5909ee

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

Researcher Bias: The Use of Machine Learning in Software Defect Prediction (2014, methodology): “Table 6 Variables Used in the Meta-analysis Variable Explanation MCC Matthews correlation coefficient also known as φ Year Date of study publication ClassifierFamily The class of classifier e.g. regression, case-based reasoner, etc. DatasetFamily The data set family (excludes version number) used fo”
Data Quality: Some Comments on the NASA Software Defect Datasets (2013, methodology): “[7] found more than a quarter of relevant defect prediction studies, that is, 58 out of 208, made use of the NASA datasets).”
The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models (2018, background): “been studied in defect prediction domain [32], [33], [34], [58], [59], [60].”
Revisiting the Impact of Classification Techniques on the Performance of Defect Prediction Models (2015, methodology): “To perform defect prediction studies [21, 58], researchers have explored the use of various classification techniques to train defect prediction models [12, 34].”
Automated Parameter Optimization of Classification Techniques for Defect Prediction Models (2016, background): “Nevertheless, we find that the optimal #boosting iterations parameter is 40, suggesting that the default parameter settings of the research toolkits are suboptimal for defect prediction datasets, which agrees with the suspicion of prior studies [15, 22, 51, 58].”
Software defect prediction using ensemble learning on selected features (2015, background): “Although there have been questions raised about the quality of these datasets [45], yet these datasets have been widely used by researchers [56].”
The Impact of Automated Parameter Optimization on Defect Prediction Models (2018, background): “This finding provides supporting evidence of the suspicions of prior studies [44], [62], [127], [145].”
Software fault prediction metrics: A systematic literature review (2013, methodology): “[23] for size, complexity and OO metrics, but differ regarding process metrics.”
An Empirical Comparison of Model Validation Techniques for Defect Prediction Models (2017, methodology): “Thus, we select a sample from the JM1 dataset such that the EPV is 3.”