Ensemble of software defect predictors: A case study

Ayse Tosun; Burak Turhan; Ayse Bener

doi:10.1145/1414004.1414066

Ensemble of software defect predictors: A case study

Ayse Tosun, Burak Turhan, Ayse Bener

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

33 Citations (Scopus)

Abstract

In this paper, we present a defect prediction model based on ensemble of classifiers, which has not been fully explored so far in this type of research. We have conducted several experiments on public datasets. Our results reveal that ensemble of classifiers considerably improve the defect detection capability compared to Naive Bayes algorithm. We also conduct a cost-benefit analysis for our ensemble, where it turns out that it is enough to inspect 32% of the code on the average, for detecting 76% of the defects.

Original language	English
Title of host publication	ESEM'08
Subtitle of host publication	Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement
Pages	318-320
Number of pages	3
DOIs	https://doi.org/10.1145/1414004.1414066
Publication status	Published - 1 Dec 2008
Externally published	Yes
Event	2nd International Symposium on Empirical Software Engineering and Measurement, ESEM 2008 - Kaiserslautern, Germany Duration: 9 Oct 2008 → 10 Oct 2008

Conference

Conference	2nd International Symposium on Empirical Software Engineering and Measurement, ESEM 2008
Country	Germany
City	Kaiserslautern
Period	9/10/08 → 10/10/08

Keywords

Defect prediction
Ensemble of classifiers
Static code attributes

Access to Document

10.1145/1414004.1414066

Link to publication in Scopus

Cite this

@inproceedings{b2c54e30fda849feba29a8b2a25710f5,

title = "Ensemble of software defect predictors: A case study",

abstract = "In this paper, we present a defect prediction model based on ensemble of classifiers, which has not been fully explored so far in this type of research. We have conducted several experiments on public datasets. Our results reveal that ensemble of classifiers considerably improve the defect detection capability compared to Naive Bayes algorithm. We also conduct a cost-benefit analysis for our ensemble, where it turns out that it is enough to inspect 32% of the code on the average, for detecting 76% of the defects.",

keywords = "Defect prediction, Ensemble of classifiers, Static code attributes",

author = "Ayse Tosun and Burak Turhan and Ayse Bener",

year = "2008",

month = dec,

day = "1",

doi = "10.1145/1414004.1414066",

language = "English",

isbn = "9781595939715",

pages = "318--320",

booktitle = "ESEM'08",

note = "2nd International Symposium on Empirical Software Engineering and Measurement, ESEM 2008 ; Conference date: 09-10-2008 Through 10-10-2008",

}

Tosun, A, Turhan, B & Bener, A 2008, Ensemble of software defect predictors: A case study. in ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement. pp. 318-320, 2nd International Symposium on Empirical Software Engineering and Measurement, ESEM 2008, Kaiserslautern, Germany, 9/10/08. https://doi.org/10.1145/1414004.1414066

TY - GEN

T1 - Ensemble of software defect predictors

T2 - 2nd International Symposium on Empirical Software Engineering and Measurement, ESEM 2008

AU - Tosun, Ayse

AU - Turhan, Burak

AU - Bener, Ayse

PY - 2008/12/1

Y1 - 2008/12/1

N2 - In this paper, we present a defect prediction model based on ensemble of classifiers, which has not been fully explored so far in this type of research. We have conducted several experiments on public datasets. Our results reveal that ensemble of classifiers considerably improve the defect detection capability compared to Naive Bayes algorithm. We also conduct a cost-benefit analysis for our ensemble, where it turns out that it is enough to inspect 32% of the code on the average, for detecting 76% of the defects.

AB - In this paper, we present a defect prediction model based on ensemble of classifiers, which has not been fully explored so far in this type of research. We have conducted several experiments on public datasets. Our results reveal that ensemble of classifiers considerably improve the defect detection capability compared to Naive Bayes algorithm. We also conduct a cost-benefit analysis for our ensemble, where it turns out that it is enough to inspect 32% of the code on the average, for detecting 76% of the defects.

KW - Defect prediction

KW - Ensemble of classifiers

KW - Static code attributes

UR - http://www.scopus.com/inward/record.url?scp=62949247536&partnerID=8YFLogxK

U2 - 10.1145/1414004.1414066

DO - 10.1145/1414004.1414066

M3 - Conference Paper

AN - SCOPUS:62949247536

SN - 9781595939715

SP - 318

EP - 320

BT - ESEM'08

Y2 - 9 October 2008 through 10 October 2008

ER -