A systematic and comprehensive investigation of methods to build and evaluate fault prediction models

By Erik Arisholm, Lionel Claude Briand, Eivind B. Johannessen. Journal of Systems and Software, 2010

482 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/de76242b3438f933c6677af28e7adb6aa9323500

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

A Survey on Software Fault Localization (2016, unknown): “Many studies that evaluate the effectiveness of speciﬁc fault localization techniques have been reported [8], [10], [11], [12], [25], [31], [36], [49], [53], [91], [93], [94], [102], [124], [178], [185], [191], [207], [209], [253], [266], [267], [296], [299], [335], [366], [390], [391], [393],…”
Using Class Imbalance Learning for Software Defect Prediction (2013, background): “5 decision trees was also found to be effective in some studies [7], [8].”
Software fault prediction metrics: A systematic literature review (2013, methodology): “The study is concluded in Section 5.”
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.”
A large-scale empirical study of just-in-time quality assurance (2013, background): “Mende and Koschke [35] use the number of lines of code as a measure of reviewing effort, similarly to Arisholm et al. [2].”
An Empirical Comparison of Model Validation Techniques for Defect Prediction Models (2017, unknown): “5) [1], [5], [62], [86], [95], and (2) are sensitive to imbalanced data [23], [44], [64], [67], [103].”
Searching for rules to detect defective modules: A subgroup discovery approach (2012, unknown): “[3] compare different data mining techniques (classification tree algorithm (C4.”
Evaluating defect prediction approaches: a benchmark and an extensive comparison (2011, methodology): “The bug prediction approach based on previous defects, proposed by Zimmermann et al. [ZPZ07], states that the number of past bug fixes extracted from the repository is correlated with the number of future fixes.”
How, and why, process metrics are better (2013, background): “[2] compared various metrics and prediction techniques on several releases of a legacy Java middleware system named COS and found that code metrics may perform well in terms of traditional performance measures such as AUC while it may not be cost-effective.”
The Impact of Automated Parameter Optimization on Defect Prediction Models (2018, background): “because they: (1) depend on an arbitrarily-selected threshold [1], [5], [80], [113], [124], [136] and (2) are sensitive to imbalanced data [24], [50], [84], [92], [132], [136].”
Software fault prediction: A literature review and current trends (2011, background): “Arisholma, Briand, and Johannessen (2010) evaluated fault-proneness models on a large Java legacy system project.”