The effect of granularity level on software defect prediction

Gul Calikli*, Ayse Tosun, Ayse Bener, Melih Celik

*Corresponding author for this work

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

10 Citations (Scopus)

Abstract

Application of defect predictors in software development helps the managers to allocate their resources such as time and effort more efficiently and cost effectively to test certain sections of the code. In this research, we have used Naïve Bayes Classifier (NBC) to construct our defect prediction framework. Our proposed framework uses the hierarchical structure information about the source code of the software product, to perform defect prediction at a functional method level and source file level. We have applied our model on SoftLAB and Eclipse datasets. We have measured the performance of our proposed model and applied cost benefit analysis. Our results reveal that source file level defect prediction improves the verification effort, while decreasing the defect prediction performance in all datasets.

Original languageEnglish
Title of host publication2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009
Pages531-536
Number of pages6
DOIs
Publication statusPublished - 2009
Externally publishedYes
Event2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009 - Guzelyurt, Cyprus
Duration: 14 Sept 200916 Sept 2009

Publication series

Name2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009

Conference

Conference2009 24th International Symposium on Computer and Information Sciences, ISCIS 2009
Country/TerritoryCyprus
CityGuzelyurt
Period14/09/0916/09/09

Keywords

  • Component
  • Cost-benefit analysis
  • Defect prediciton
  • Naïve Bayes Classifier
  • Static code attributes

Fingerprint

Dive into the research topics of 'The effect of granularity level on software defect prediction'. Together they form a unique fingerprint.

Cite this