Predicting defect-prone software modules using support vector machines

By Karim O. Elish, Mahmoud O. Elish. Journal of Systems and Software, 2008

550 citations recorded by the source corpus.

Subfields: Information Systems, Software

View Paper: https://www.semanticscholar.org/paper/a86f2fe910c54c8f41cd08c8a68f989511522fdb

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 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.”
Easy over hard: a case study on deep learning (2017, background): “[18] compared support vector machines to other data miners for the purposes of defect prediction.”
Automatically Learning Semantic Features for Defect Prediction (2016, methodology): “Elish et al. [8] evaluated the capability of SVM in predicting defect-prone software modules, and they compared SVM against eight statistical and machine learning models on four NASA datasets.”
Software Defect Prediction via Convolutional Neural Network (2017, methodology): “[33] evaluated the feasibility of Support Vector Machine (SVM) in predicting defect-prone software modules, and they compared SVM with other eight statistical learning methods on four NASA datasets.”
Software fault prediction metrics: A systematic literature review (2013, methodology): “1 Model performance is inﬂuenced by a modeling technique [9,16,20,29,30] and metrics [89,138,130,88,66].”
A General Software Defect-Proneness Prediction Framework (2011, methodology): “We used the data taken from the public NASA MDP repository [37], which was also used by MGF and many others, e.g., [24], [38], [39], and [22].”
Searching for rules to detect defective modules: A subgroup discovery approach (2012, background): “…of classifiers is the f measure [57] as an harmonic median of these two proportions: f measure ¼ 2 precision recall precisionþ recall ¼ 2 TP 2 TP þ FP þ FN ; ð2Þ where precision (precision ¼ TPTPþFP) is the proportion of positive predictions that are correct and recall is the TPr…”
A systematic and comprehensive investigation of methods to build and evaluate fault prediction models (2010, methodology): “Elish and Elish (2008) compared SVM against eight other modeling techniques , among them Random Forest.”