An over-sampling method for analogy-based software effort estimation

Yasutaka Kamei; Jacky Keung; Akito Monden; Ken Ichi Matsumoto

doi:10.1145/1414004.1414064

An over-sampling method for analogy-based software effort estimation

Yasutaka Kamei, Jacky Keung, Akito Monden, Ken Ichi Matsumoto

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Citations (Scopus)

Abstract

This paper proposes a novel method to generate synthetic project cases and add them to a fit dataset for the purpose of improving the performance of analogy-based software effort estimation. The proposed method extends conventional over-sampling method, which is a preprocessing procedure for n-group classification problems, which makes it suitable for any unbalanced dataset to be used in analogy-based system. We experimentally evaluated the effect of the over-sampling method to improve the performance of the analogy-based software effort estimation by using the Desharnais dataset. Results show significant improvement to the estimation accuracy by using our approach.

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	312-314
Number of pages	3
DOIs	https://doi.org/10.1145/1414004.1414064
Publication status	Published - Dec 1 2008
Externally published	Yes
Event	2nd International Symposium on Empirical Software Engineering and Measurement, ESEM 2008 - Kaiserslautern, Germany Duration: Oct 9 2008 → Oct 10 2008

Publication series

Name	ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement

Other

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

Keywords

Analogy
Empirical study
Over-sampling
Software effort estimation

ASJC Scopus subject areas

Computer Science Applications
Software
Electrical and Electronic Engineering

Access to Document

10.1145/1414004.1414064

Cite this

Kamei, Y., Keung, J., Monden, A., & Matsumoto, K. I. (2008). An over-sampling method for analogy-based software effort estimation. In ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement (pp. 312-314). (ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement). https://doi.org/10.1145/1414004.1414064

An over-sampling method for analogy-based software effort estimation. / Kamei, Yasutaka; Keung, Jacky; Monden, Akito et al.
ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement. 2008. p. 312-314 (ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kamei, Y, Keung, J, Monden, A & Matsumoto, KI 2008, An over-sampling method for analogy-based software effort estimation. in ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement. ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement, pp. 312-314, 2nd International Symposium on Empirical Software Engineering and Measurement, ESEM 2008, Kaiserslautern, Germany, 10/9/08. https://doi.org/10.1145/1414004.1414064

Kamei Y, Keung J, Monden A, Matsumoto KI. An over-sampling method for analogy-based software effort estimation. In ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement. 2008. p. 312-314. (ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement). doi: 10.1145/1414004.1414064

Kamei, Yasutaka ; Keung, Jacky ; Monden, Akito et al. / An over-sampling method for analogy-based software effort estimation. ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement. 2008. pp. 312-314 (ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement).

@inproceedings{d66114a7c1a84d078364c4b4a3bda749,

title = "An over-sampling method for analogy-based software effort estimation",

abstract = "This paper proposes a novel method to generate synthetic project cases and add them to a fit dataset for the purpose of improving the performance of analogy-based software effort estimation. The proposed method extends conventional over-sampling method, which is a preprocessing procedure for n-group classification problems, which makes it suitable for any unbalanced dataset to be used in analogy-based system. We experimentally evaluated the effect of the over-sampling method to improve the performance of the analogy-based software effort estimation by using the Desharnais dataset. Results show significant improvement to the estimation accuracy by using our approach.",

keywords = "Analogy, Empirical study, Over-sampling, Software effort estimation",

author = "Yasutaka Kamei and Jacky Keung and Akito Monden and Matsumoto, {Ken Ichi}",

year = "2008",

month = dec,

day = "1",

doi = "10.1145/1414004.1414064",

language = "English",

isbn = "9781595939715",

series = "ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement",

pages = "312--314",

booktitle = "ESEM'08",

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

}

TY - GEN

T1 - An over-sampling method for analogy-based software effort estimation

AU - Kamei, Yasutaka

AU - Keung, Jacky

AU - Monden, Akito

AU - Matsumoto, Ken Ichi

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This paper proposes a novel method to generate synthetic project cases and add them to a fit dataset for the purpose of improving the performance of analogy-based software effort estimation. The proposed method extends conventional over-sampling method, which is a preprocessing procedure for n-group classification problems, which makes it suitable for any unbalanced dataset to be used in analogy-based system. We experimentally evaluated the effect of the over-sampling method to improve the performance of the analogy-based software effort estimation by using the Desharnais dataset. Results show significant improvement to the estimation accuracy by using our approach.

AB - This paper proposes a novel method to generate synthetic project cases and add them to a fit dataset for the purpose of improving the performance of analogy-based software effort estimation. The proposed method extends conventional over-sampling method, which is a preprocessing procedure for n-group classification problems, which makes it suitable for any unbalanced dataset to be used in analogy-based system. We experimentally evaluated the effect of the over-sampling method to improve the performance of the analogy-based software effort estimation by using the Desharnais dataset. Results show significant improvement to the estimation accuracy by using our approach.

KW - Analogy

KW - Empirical study

KW - Over-sampling

KW - Software effort estimation

UR - http://www.scopus.com/inward/record.url?scp=62949141179&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62949141179&partnerID=8YFLogxK

U2 - 10.1145/1414004.1414064

DO - 10.1145/1414004.1414064

M3 - Conference contribution

AN - SCOPUS:62949141179

SN - 9781595939715

T3 - ESEM'08: Proceedings of the 2008 ACM-IEEE International Symposium on Empirical Software Engineering and Measurement

SP - 312

EP - 314

BT - ESEM'08

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

Y2 - 9 October 2008 through 10 October 2008

ER -

An over-sampling method for analogy-based software effort estimation

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this