Skip to main navigation Skip to search Skip to main content

Improving prediction robustness of VAB-SVM for cross-project defect prediction

  • Korea Advanced Institute of Science and Technology

Research output: Contribution to conferenceConference paperpeer-review

Abstract

Software defect prediction is important for improving software quality. Defect predictors allow software test engineers to focus on defective modules. Cross-Project Defect Prediction (CPDP) uses data from other companies to build defect predictors. However, outliers may lower prediction accuracy. In this study, we propose a transfer learning based model called VAB-SVM for CPDP robust in handling outliers. Notably, this method deals with the class imbalance problem which may decrease the prediction accuracy. Our proposed method computes similarity weights of the training data based on the test data. Such weights are applied to Boosting algorithm considering the class imbalance. VAB-SVM outperformed the previous research more than 10% and showed a sufficient robustness regardless of the ratio of outliers.

Original languageEnglish
Title of host publicationProceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014
EditorsXingang Liu, Didier El Baz, Ching-Hsien Hsu, Kai Kang, Weifeng Chen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages994-999
Number of pages6
ISBN (Electronic)9781479979813
DOIs
StatePublished - 2015.01.26
Event17th IEEE International Conference on Computational Science and Engineering, CSE 2014 - Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014 - Chengdu, China
Duration: 2014.12.192014.12.21

Publication series

NameProceedings - 17th IEEE International Conference on Computational Science and Engineering, CSE 2014, Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014

Conference

Conference17th IEEE International Conference on Computational Science and Engineering, CSE 2014 - Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications, IUCC 2014, 13th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2014 and 8th International Conference on Frontier of Computer Science and Technology, FCST 2014
Country/TerritoryChina
CityChengdu
Period14.12.1914.12.21

Keywords

  • Boosting
  • Cross-project defect prediction
  • Outlier detection
  • Transfer learning

Fingerprint

Dive into the research topics of 'Improving prediction robustness of VAB-SVM for cross-project defect prediction'. Together they form a unique fingerprint.

Cite this