Reducing false alarms in software defect prediction by decision threshold optimization

Authors:
Ayse Tosun;Ayse Bener
Affiliations:
Software Research Laboratory, Computer Engineering Department, Bogazici University Istanbul, Turkey;Software Research Laboratory, Computer Engineering Department, Bogazici University Istanbul, Turkey
Venue:
ESEM '09 Proceedings of the 2009 3rd International Symposium on Empirical Software Engineering and Measurement
Year:
2009

Citing 9
Cited 2

Introduction to Machine Learning (Adaptive Computation and Machine Learning)

Introduction to Machine Learning (Adaptive Computation and Machine Learning)
An introduction to ROC analysis

Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
Data Mining Static Code Attributes to Learn Defect Predictors

IEEE Transactions on Software Engineering
The Effects of Over and Under Sampling on Fault-prone Module Detection

ESEM '07 Proceedings of the First International Symposium on Empirical Software Engineering and Measurement
A comparative analysis of the efficiency of change metrics and static code attributes for defect prediction

Proceedings of the 30th international conference on Software engineering
Nearest neighbor sampling for cross company defect predictors: abstract only

DEFECTS '08 Proceedings of the 2008 workshop on Defects in large software systems
Ensemble of software defect predictors: a case study

Proceedings of the Second ACM-IEEE international symposium on Empirical software engineering and measurement
Benchmarking Classification Models for Software Defect Prediction: A Proposed Framework and Novel Findings

IEEE Transactions on Software Engineering
On the relative value of cross-company and within-company data for defect prediction

Empirical Software Engineering

Practical considerations in deploying statistical methods for defect prediction: A case study within the Turkish telecommunications industry

Information and Software Technology
Defect prediction using social network analysis on issue repositories

Proceedings of the 2011 International Conference on Software and Systems Process

Quantified Score

Hi-index	0.00

Visualization

Abstract

Software defect data has an imbalanced and highly skewed class distribution. The misclassification costs of two classes are not equal nor are known. It is critical to find the optimum bound, i.e. threshold, which would best separate defective and defect-free classes in software data. We have applied decision threshold optimization on Naïve Bayes classifier in order to find the optimum threshold for software defect data. ROC analyses show that decision threshold optimization significantly decreases false alarms (on the average by 11%) without changing probability of detection rates.