A learning-to-rank algorithm for constructing defect prediction models

Xiaoxing YANG, Ke TANG, Xin YAO

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

14 Citations (Scopus)

Abstract

This paper applies the learning-to-rank approach to software defect prediction. Ranking software modules in order of defect-proneness is important to ensure that testing resources are allocated efficiently. However, prediction models that are optimized for predicting explicitly the number of defects often fail to correctly predict rankings based on those defect numbers. We show in this paper that the model construction methods, which include the ranking performance measure in the objective function, perform better in predicting defect-proneness rankings of multiple modules. We present the experimental results, in which our method is compared against three other methods from the literature, using five publicly available data sets. © 2012 Springer-Verlag.
Original languageEnglish
Title of host publicationIntelligent Data Engineering and Automated Learning : IDEAL 2012 : 13th International Conference, Natal, Brazil, August 29-31, 2012, Proceedings
EditorsHujun YIN, José A. F. COSTA, Guilherme BARRETO
PublisherSpringer Berlin Heidelberg
Pages167-175
Number of pages9
ISBN (Electronic)9783642326394
ISBN (Print)9783642326387
DOIs
Publication statusPublished - 2012
Externally publishedYes
Event13th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2012 - Natal, Brazil
Duration: 29 Aug 201231 Aug 2012

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin, Heidelberg
Volume7435
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference13th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2012
Country/TerritoryBrazil
CityNatal
Period29/08/1231/08/12

Keywords

  • differential evolution
  • Learning-to-rank
  • software defect prediction

Fingerprint

Dive into the research topics of 'A learning-to-rank algorithm for constructing defect prediction models'. Together they form a unique fingerprint.

Cite this