An Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction

Ranking-oriented cross-project defect prediction (ROCPDP), which ranks software modules of a new target industrial project based on the predicted defect number or density, has been suggested in the literature. A major concern of ROCPDP is the distribution difference between the source project (aka....

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Haoyu Luo, Heng Dai, Weiqiang Peng, Wenhua Hu, Fuyang Li
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/59a58f66c75b4c9ba2125e2709250132
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:59a58f66c75b4c9ba2125e2709250132
record_format dspace
spelling oai:doaj.org-article:59a58f66c75b4c9ba2125e27092501322021-11-25T18:57:14ZAn Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction10.3390/s212275351424-8220https://doaj.org/article/59a58f66c75b4c9ba2125e27092501322021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7535https://doaj.org/toc/1424-8220Ranking-oriented cross-project defect prediction (ROCPDP), which ranks software modules of a new target industrial project based on the predicted defect number or density, has been suggested in the literature. A major concern of ROCPDP is the distribution difference between the source project (aka. within-project) data and target project (aka. cross-project) data, which evidently degrades prediction performance. To investigate the impacts of training data selection methods on the performances of ROCPDP models, we examined the practical effects of nine training data selection methods, including a global filter, which does not filter out any cross-project data. Additionally, the prediction performances of ROCPDP models trained on the filtered cross-project data using the training data selection methods were compared with those of ranking-oriented within-project defect prediction (ROWPDP) models trained on sufficient and limited within-project data. Eleven available defect datasets from the industrial projects were considered and evaluated using two ranking performance measures, i.e., FPA and Norm(Popt). The results showed no statistically significant differences among these nine training data selection methods in terms of FPA and Norm(Popt). The performances of ROCPDP models trained on filtered cross-project data were not comparable with those of ROWPDP models trained on sufficient historical within-project data. However, ROCPDP models trained on filtered cross-project data achieved better performance values than ROWPDP models trained on limited historical within-project data. Therefore, we recommended that software quality teams exploit other project datasets to perform ROCPDP when there is no or limited within-project data.Haoyu LuoHeng DaiWeiqiang PengWenhua HuFuyang LiMDPI AGarticlefault predictionmachine learningdata selectionChemical technologyTP1-1185ENSensors, Vol 21, Iss 7535, p 7535 (2021)
institution DOAJ
collection DOAJ
language EN
topic fault prediction
machine learning
data selection
Chemical technology
TP1-1185
spellingShingle fault prediction
machine learning
data selection
Chemical technology
TP1-1185
Haoyu Luo
Heng Dai
Weiqiang Peng
Wenhua Hu
Fuyang Li
An Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction
description Ranking-oriented cross-project defect prediction (ROCPDP), which ranks software modules of a new target industrial project based on the predicted defect number or density, has been suggested in the literature. A major concern of ROCPDP is the distribution difference between the source project (aka. within-project) data and target project (aka. cross-project) data, which evidently degrades prediction performance. To investigate the impacts of training data selection methods on the performances of ROCPDP models, we examined the practical effects of nine training data selection methods, including a global filter, which does not filter out any cross-project data. Additionally, the prediction performances of ROCPDP models trained on the filtered cross-project data using the training data selection methods were compared with those of ranking-oriented within-project defect prediction (ROWPDP) models trained on sufficient and limited within-project data. Eleven available defect datasets from the industrial projects were considered and evaluated using two ranking performance measures, i.e., FPA and Norm(Popt). The results showed no statistically significant differences among these nine training data selection methods in terms of FPA and Norm(Popt). The performances of ROCPDP models trained on filtered cross-project data were not comparable with those of ROWPDP models trained on sufficient historical within-project data. However, ROCPDP models trained on filtered cross-project data achieved better performance values than ROWPDP models trained on limited historical within-project data. Therefore, we recommended that software quality teams exploit other project datasets to perform ROCPDP when there is no or limited within-project data.
format article
author Haoyu Luo
Heng Dai
Weiqiang Peng
Wenhua Hu
Fuyang Li
author_facet Haoyu Luo
Heng Dai
Weiqiang Peng
Wenhua Hu
Fuyang Li
author_sort Haoyu Luo
title An Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction
title_short An Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction
title_full An Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction
title_fullStr An Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction
title_full_unstemmed An Empirical Study of Training Data Selection Methods for Ranking-Oriented Cross-Project Defect Prediction
title_sort empirical study of training data selection methods for ranking-oriented cross-project defect prediction
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/59a58f66c75b4c9ba2125e2709250132
work_keys_str_mv AT haoyuluo anempiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT hengdai anempiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT weiqiangpeng anempiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT wenhuahu anempiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT fuyangli anempiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT haoyuluo empiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT hengdai empiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT weiqiangpeng empiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT wenhuahu empiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
AT fuyangli empiricalstudyoftrainingdataselectionmethodsforrankingorientedcrossprojectdefectprediction
_version_ 1718410524203417600