Cross-Project Change-Proneness prediction

Chao Liu, Dan Yang, Xin Xia, Meng Yan, Xiaohong Zhang

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

Abstract

Software change-proneness prediction (whether or not class files in a project will be changed in the next release) can help software developers to focus on preventive actions to reduce maintenance costs, and managers to allocate resources more effectively. Prior studies found that change-proneness prediction works well if there is sufficient amount of training data to build a model. However, it is not feasible for projects with limited historical data especially for new projects. To address this issue, cross-project change-proneness prediction, which builds a prediction model by using data in another project (i.e., source project), and predicts the change-proneness in a target project, is proposed. Considering there are a large number of source projects, one challenge for cross-project change-proneness prediction is that given a target project, how to automatically select a source project which could show good prediction accuracy on it. In this paper, we propose a selective cross-project (SCP) model for change-proneness prediction. SCP automatically finds the source project which has the similar data distribution with the target project by measuring distribution similarity between source and target projects. We evaluate SCP by conducting an empirical study on 14 open source projects. We compare it with 2 most related change-proneness models, including RCP (Random Cross-Project prediction) proposed by Malhotra and Bansal, and CLAMI+ developed by Yan et al. Experiment results show that SCP improves RCP and CLAMI+ by 25.34% and 4.30% in terms of AUC respectively; and by 171.42% and 172.31% in terms of cost-effectiveness, respectively.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018
Subtitle of host publication23-27 July 2018 Tokyo, Japan
EditorsSorel Reisman, Sheikh Iqbal Ahamed, Claudio Demartini, Thomas Conte, Ling Liu, William Claycomb, Motonori Nakamura, Edmundo Tovar, Stelvio Cimato, Chung-Horng Lung, Hiroki Takakura, Ji-Jiang Yang, Toyokazu Akiyama, Zhiyong Zhang, Kamrul Hasan
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages64-73
Number of pages10
Volume1
ISBN (Print)9781538626665
DOIs
Publication statusPublished - 2018
EventInternational Computer Software and Applications Conference 2018 - Tokyo, Japan
Duration: 23 Jul 201827 Jul 2018
Conference number: 42nd
https://ieeecompsac.computer.org/2018/

Conference

ConferenceInternational Computer Software and Applications Conference 2018
Abbreviated titleCOMPSAC 2018
CountryJapan
CityTokyo
Period23/07/1827/07/18
Internet address

Keywords

  • Change-Proneness
  • Cross-Project Prediction
  • Maintainability
  • Project Selection

Cite this

Liu, C., Yang, D., Xia, X., Yan, M., & Zhang, X. (2018). Cross-Project Change-Proneness prediction. In S. Reisman, S. Iqbal Ahamed, C. Demartini, T. Conte, L. Liu, W. Claycomb, M. Nakamura, E. Tovar, S. Cimato, C-H. Lung, H. Takakura, J-J. Yang, T. Akiyama, Z. Zhang, ... K. Hasan (Eds.), Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018: 23-27 July 2018 Tokyo, Japan (Vol. 1, pp. 64-73). [8377641] Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/COMPSAC.2018.00017
Liu, Chao ; Yang, Dan ; Xia, Xin ; Yan, Meng ; Zhang, Xiaohong. / Cross-Project Change-Proneness prediction. Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018: 23-27 July 2018 Tokyo, Japan. editor / Sorel Reisman ; Sheikh Iqbal Ahamed ; Claudio Demartini ; Thomas Conte ; Ling Liu ; William Claycomb ; Motonori Nakamura ; Edmundo Tovar ; Stelvio Cimato ; Chung-Horng Lung ; Hiroki Takakura ; Ji-Jiang Yang ; Toyokazu Akiyama ; Zhiyong Zhang ; Kamrul Hasan. Vol. 1 Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 64-73
@inproceedings{c9c863737caf417ea309b8e6c2ce3824,
title = "Cross-Project Change-Proneness prediction",
abstract = "Software change-proneness prediction (whether or not class files in a project will be changed in the next release) can help software developers to focus on preventive actions to reduce maintenance costs, and managers to allocate resources more effectively. Prior studies found that change-proneness prediction works well if there is sufficient amount of training data to build a model. However, it is not feasible for projects with limited historical data especially for new projects. To address this issue, cross-project change-proneness prediction, which builds a prediction model by using data in another project (i.e., source project), and predicts the change-proneness in a target project, is proposed. Considering there are a large number of source projects, one challenge for cross-project change-proneness prediction is that given a target project, how to automatically select a source project which could show good prediction accuracy on it. In this paper, we propose a selective cross-project (SCP) model for change-proneness prediction. SCP automatically finds the source project which has the similar data distribution with the target project by measuring distribution similarity between source and target projects. We evaluate SCP by conducting an empirical study on 14 open source projects. We compare it with 2 most related change-proneness models, including RCP (Random Cross-Project prediction) proposed by Malhotra and Bansal, and CLAMI+ developed by Yan et al. Experiment results show that SCP improves RCP and CLAMI+ by 25.34{\%} and 4.30{\%} in terms of AUC respectively; and by 171.42{\%} and 172.31{\%} in terms of cost-effectiveness, respectively.",
keywords = "Change-Proneness, Cross-Project Prediction, Maintainability, Project Selection",
author = "Chao Liu and Dan Yang and Xin Xia and Meng Yan and Xiaohong Zhang",
year = "2018",
doi = "10.1109/COMPSAC.2018.00017",
language = "English",
isbn = "9781538626665",
volume = "1",
pages = "64--73",
editor = "Sorel Reisman and {Iqbal Ahamed}, {Sheikh } and Demartini, {Claudio } and Conte, {Thomas } and Liu, {Ling } and Claycomb, {William } and Nakamura, {Motonori } and Tovar, {Edmundo } and Stelvio Cimato and Lung, {Chung-Horng } and Takakura, {Hiroki } and Yang, {Ji-Jiang } and Toyokazu Akiyama and Zhang, {Zhiyong } and Hasan, {Kamrul }",
booktitle = "Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
address = "United States of America",

}

Liu, C, Yang, D, Xia, X, Yan, M & Zhang, X 2018, Cross-Project Change-Proneness prediction. in S Reisman, S Iqbal Ahamed, C Demartini, T Conte, L Liu, W Claycomb, M Nakamura, E Tovar, S Cimato, C-H Lung, H Takakura, J-J Yang, T Akiyama, Z Zhang & K Hasan (eds), Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018: 23-27 July 2018 Tokyo, Japan. vol. 1, 8377641, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 64-73, International Computer Software and Applications Conference 2018, Tokyo, Japan, 23/07/18. https://doi.org/10.1109/COMPSAC.2018.00017

Cross-Project Change-Proneness prediction. / Liu, Chao; Yang, Dan; Xia, Xin; Yan, Meng; Zhang, Xiaohong.

Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018: 23-27 July 2018 Tokyo, Japan. ed. / Sorel Reisman; Sheikh Iqbal Ahamed; Claudio Demartini; Thomas Conte; Ling Liu; William Claycomb; Motonori Nakamura; Edmundo Tovar; Stelvio Cimato; Chung-Horng Lung; Hiroki Takakura; Ji-Jiang Yang; Toyokazu Akiyama; Zhiyong Zhang; Kamrul Hasan. Vol. 1 Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 64-73 8377641.

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

TY - GEN

T1 - Cross-Project Change-Proneness prediction

AU - Liu, Chao

AU - Yang, Dan

AU - Xia, Xin

AU - Yan, Meng

AU - Zhang, Xiaohong

PY - 2018

Y1 - 2018

N2 - Software change-proneness prediction (whether or not class files in a project will be changed in the next release) can help software developers to focus on preventive actions to reduce maintenance costs, and managers to allocate resources more effectively. Prior studies found that change-proneness prediction works well if there is sufficient amount of training data to build a model. However, it is not feasible for projects with limited historical data especially for new projects. To address this issue, cross-project change-proneness prediction, which builds a prediction model by using data in another project (i.e., source project), and predicts the change-proneness in a target project, is proposed. Considering there are a large number of source projects, one challenge for cross-project change-proneness prediction is that given a target project, how to automatically select a source project which could show good prediction accuracy on it. In this paper, we propose a selective cross-project (SCP) model for change-proneness prediction. SCP automatically finds the source project which has the similar data distribution with the target project by measuring distribution similarity between source and target projects. We evaluate SCP by conducting an empirical study on 14 open source projects. We compare it with 2 most related change-proneness models, including RCP (Random Cross-Project prediction) proposed by Malhotra and Bansal, and CLAMI+ developed by Yan et al. Experiment results show that SCP improves RCP and CLAMI+ by 25.34% and 4.30% in terms of AUC respectively; and by 171.42% and 172.31% in terms of cost-effectiveness, respectively.

AB - Software change-proneness prediction (whether or not class files in a project will be changed in the next release) can help software developers to focus on preventive actions to reduce maintenance costs, and managers to allocate resources more effectively. Prior studies found that change-proneness prediction works well if there is sufficient amount of training data to build a model. However, it is not feasible for projects with limited historical data especially for new projects. To address this issue, cross-project change-proneness prediction, which builds a prediction model by using data in another project (i.e., source project), and predicts the change-proneness in a target project, is proposed. Considering there are a large number of source projects, one challenge for cross-project change-proneness prediction is that given a target project, how to automatically select a source project which could show good prediction accuracy on it. In this paper, we propose a selective cross-project (SCP) model for change-proneness prediction. SCP automatically finds the source project which has the similar data distribution with the target project by measuring distribution similarity between source and target projects. We evaluate SCP by conducting an empirical study on 14 open source projects. We compare it with 2 most related change-proneness models, including RCP (Random Cross-Project prediction) proposed by Malhotra and Bansal, and CLAMI+ developed by Yan et al. Experiment results show that SCP improves RCP and CLAMI+ by 25.34% and 4.30% in terms of AUC respectively; and by 171.42% and 172.31% in terms of cost-effectiveness, respectively.

KW - Change-Proneness

KW - Cross-Project Prediction

KW - Maintainability

KW - Project Selection

UR - http://www.scopus.com/inward/record.url?scp=85055440637&partnerID=8YFLogxK

U2 - 10.1109/COMPSAC.2018.00017

DO - 10.1109/COMPSAC.2018.00017

M3 - Conference Paper

SN - 9781538626665

VL - 1

SP - 64

EP - 73

BT - Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018

A2 - Reisman, Sorel

A2 - Iqbal Ahamed, Sheikh

A2 - Demartini, Claudio

A2 - Conte, Thomas

A2 - Liu, Ling

A2 - Claycomb, William

A2 - Nakamura, Motonori

A2 - Tovar, Edmundo

A2 - Cimato, Stelvio

A2 - Lung, Chung-Horng

A2 - Takakura, Hiroki

A2 - Yang, Ji-Jiang

A2 - Akiyama, Toyokazu

A2 - Zhang, Zhiyong

A2 - Hasan, Kamrul

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

ER -

Liu C, Yang D, Xia X, Yan M, Zhang X. Cross-Project Change-Proneness prediction. In Reisman S, Iqbal Ahamed S, Demartini C, Conte T, Liu L, Claycomb W, Nakamura M, Tovar E, Cimato S, Lung C-H, Takakura H, Yang J-J, Akiyama T, Zhang Z, Hasan K, editors, Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018: 23-27 July 2018 Tokyo, Japan. Vol. 1. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 64-73. 8377641 https://doi.org/10.1109/COMPSAC.2018.00017