Reducing false alarms in software defect prediction by decision threshold optimization

Ayşe Tosun*, Ayşe Bener

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

57 Citations (Scopus)

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.

Original languageEnglish
Title of host publication2009 3rd International Symposium on Empirical Software Engineering and Measurement, ESEM 2009
Pages477-480
Number of pages4
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 3rd International Symposium on Empirical Software Engineering and Measurement, ESEM 2009 - Lake Buena Vista, FL, United States
Duration: 15 Oct 200916 Oct 2009

Publication series

Name2009 3rd International Symposium on Empirical Software Engineering and Measurement, ESEM 2009

Conference

Conference2009 3rd International Symposium on Empirical Software Engineering and Measurement, ESEM 2009
Country/TerritoryUnited States
CityLake Buena Vista, FL
Period15/10/0916/10/09

Fingerprint

Dive into the research topics of 'Reducing false alarms in software defect prediction by decision threshold optimization'. Together they form a unique fingerprint.

Cite this