Standard

A search-based training algorithm for cost-aware defect prediction. / Panichella, Annibale; Alexandru, Carol V.; Panichella, Sebastiano; Bacchelli, Alberto; Gall, Harald C.

GECCO '16 Proceedings of the Genetic and Evolutionary Computation Conference 2016. New York : Association for Computing Machinery (ACM), 2016. p. 1077-1084.

Research output: Scientific - peer-reviewConference contribution

Harvard

Panichella, A, Alexandru, CV, Panichella, S, Bacchelli, A & Gall, HC 2016, A search-based training algorithm for cost-aware defect prediction. in GECCO '16 Proceedings of the Genetic and Evolutionary Computation Conference 2016. Association for Computing Machinery (ACM), New York, pp. 1077-1084, 2016 Genetic and Evolutionary Computation Conference, GECCO 2016, Denver, United States, 20-24 July. DOI: 10.1145/2908812.2908938

APA

Panichella, A., Alexandru, C. V., Panichella, S., Bacchelli, A., & Gall, H. C. (2016). A search-based training algorithm for cost-aware defect prediction. In GECCO '16 Proceedings of the Genetic and Evolutionary Computation Conference 2016. (pp. 1077-1084). New York: Association for Computing Machinery (ACM). DOI: 10.1145/2908812.2908938

Vancouver

Panichella A, Alexandru CV, Panichella S, Bacchelli A, Gall HC. A search-based training algorithm for cost-aware defect prediction. In GECCO '16 Proceedings of the Genetic and Evolutionary Computation Conference 2016. New York: Association for Computing Machinery (ACM). 2016. p. 1077-1084. Available from, DOI: 10.1145/2908812.2908938

Author

Panichella, Annibale; Alexandru, Carol V.; Panichella, Sebastiano; Bacchelli, Alberto; Gall, Harald C. / A search-based training algorithm for cost-aware defect prediction.

GECCO '16 Proceedings of the Genetic and Evolutionary Computation Conference 2016. New York : Association for Computing Machinery (ACM), 2016. p. 1077-1084.

Research output: Scientific - peer-reviewConference contribution

BibTeX

@inbook{67912115018847d9992367b794b83f8a,
title = "A search-based training algorithm for cost-aware defect prediction",
keywords = "Defect prediction, Genetic algorithm, Machine learning",
author = "Annibale Panichella and Alexandru, {Carol V.} and Sebastiano Panichella and Alberto Bacchelli and Gall, {Harald C.}",
year = "2016",
doi = "10.1145/2908812.2908938",
pages = "1077--1084",
booktitle = "GECCO '16 Proceedings of the Genetic and Evolutionary Computation Conference 2016",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

RIS

TY - CHAP

T1 - A search-based training algorithm for cost-aware defect prediction

AU - Panichella,Annibale

AU - Alexandru,Carol V.

AU - Panichella,Sebastiano

AU - Bacchelli,Alberto

AU - Gall,Harald C.

PY - 2016

Y1 - 2016

N2 - Research has yielded approaches to predict future defects in software artifacts based on historical information, thus assisting companies in effectively allocating limited development resources and developers in reviewing each others' code changes. Developers are unlikely to devote the same effort to inspect each software artifact predicted to contain defects, since the effort varies with the artifacts' size (cost) and the number of defects it exhibits (effectiveness). We propose to use Genetic Algorithms (GAs) for training prediction models to maximize their cost-effectiveness. We evaluate the approach on two well-known models, Regression Tree and Generalized Linear Model, and predict defects between multiple releases of six open source projects. Our results show that regression models trained by GAs significantly outperform their traditional counterparts, improving the cost-effectiveness by up to 240%. Often the top 10% of predicted lines of code contain up to twice as many defects.

AB - Research has yielded approaches to predict future defects in software artifacts based on historical information, thus assisting companies in effectively allocating limited development resources and developers in reviewing each others' code changes. Developers are unlikely to devote the same effort to inspect each software artifact predicted to contain defects, since the effort varies with the artifacts' size (cost) and the number of defects it exhibits (effectiveness). We propose to use Genetic Algorithms (GAs) for training prediction models to maximize their cost-effectiveness. We evaluate the approach on two well-known models, Regression Tree and Generalized Linear Model, and predict defects between multiple releases of six open source projects. Our results show that regression models trained by GAs significantly outperform their traditional counterparts, improving the cost-effectiveness by up to 240%. Often the top 10% of predicted lines of code contain up to twice as many defects.

KW - Defect prediction

KW - Genetic algorithm

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=84985992139&partnerID=8YFLogxK

U2 - 10.1145/2908812.2908938

DO - 10.1145/2908812.2908938

M3 - Conference contribution

SP - 1077

EP - 1084

BT - GECCO '16 Proceedings of the Genetic and Evolutionary Computation Conference 2016

PB - Association for Computing Machinery (ACM)

ER -

ID: 9302789