Revisiting the Conclusion Instability Issue in Software Effort Estimation

Michael Franklin Bosu; Solomon Mensah; Kwabena Bennin; Diab Abuaiadah

doi:10.18293/SEKE2018-126

Revisiting the Conclusion Instability Issue in Software Effort Estimation

Michael Franklin Bosu
, Solomon Mensah
, Kwabena Bennin
, Diab Abuaiadah

Department of Computer Science

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

2 Citations (Scopus)

Abstract

Conclusion instability is the absence of observing the same effect under varying experimental conditions. Deep Neural Network (DNN) and ElasticNet software effort estimation (SEE) models were applied to two SEE datasets with the view of resolving the conclusion instability issue and assessing the suitability of ElasticNet as a viable SEE benchmark model. Results were mixed as both model types attain conclusion stability for the Kitchenham dataset whilst conclusion instability existed in the Desharnais dataset. ElasticNet was outperformed by DNN and as such it is not recommended to be used as a SEE benchmark model.

Original language	English
Title of host publication	SEKE 2018: Proceedings of the 30th International Conference on Software Engineering and Knowledge Engineering
Place of Publication	Pittsburgh, PA
Publisher	Knowledge Systems Institute Graduate School
Pages	368-371
ISBN (Print)	1891706446
DOIs	https://doi.org/10.18293/SEKE2018-126
Publication status	Published - Jul 2018
Event	The 30th International Conference on Software Engineering and Knowledge Engineering (SEKE 2018) - Hotel Pullman, Redwood City, United States Duration: 1 Jul 2018 → 3 Jul 2018 http://ksiresearchorg.ipage.com/seke/seke18.html http://ksiresearchorg.ipage.com/seke/sekeproc.html

Publication series

Name	Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering, SEKE
Volume	2018
ISSN (Print)	2325-9000
ISSN (Electronic)	2325-9086

Conference

Conference	The 30th International Conference on Software Engineering and Knowledge Engineering (SEKE 2018)
Abbreviated title	SEKE 2018
Place	United States
City	Redwood City
Period	1/07/18 → 3/07/18
Internet address	http://ksiresearchorg.ipage.com/seke/seke18.html http://ksiresearchorg.ipage.com/seke/sekeproc.html

Research Keywords

Conclusion Instability
Deep Neural Network
ElasticNet
Prediction model
Software Effort Estimation

Access Output

10.18293/SEKE2018-126

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Bosu, M. F., Mensah, S., Bennin, K., & Abuaiadah, D. (2018). Revisiting the Conclusion Instability Issue in Software Effort Estimation. In SEKE 2018: Proceedings of the 30th International Conference on Software Engineering and Knowledge Engineering (pp. 368-371). (Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering, SEKE; Vol. 2018). Knowledge Systems Institute Graduate School. https://doi.org/10.18293/SEKE2018-126

Bosu, Michael Franklin ; Mensah, Solomon ; Bennin, Kwabena et al. / Revisiting the Conclusion Instability Issue in Software Effort Estimation. SEKE 2018: Proceedings of the 30th International Conference on Software Engineering and Knowledge Engineering. Pittsburgh, PA : Knowledge Systems Institute Graduate School, 2018. pp. 368-371 (Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering, SEKE).

@inproceedings{1173af4f2c174d1b8124bfbbf286f7dd,

title = "Revisiting the Conclusion Instability Issue in Software Effort Estimation",

abstract = "Conclusion instability is the absence of observing the same effect under varying experimental conditions. Deep Neural Network (DNN) and ElasticNet software effort estimation (SEE) models were applied to two SEE datasets with the view of resolving the conclusion instability issue and assessing the suitability of ElasticNet as a viable SEE benchmark model. Results were mixed as both model types attain conclusion stability for the Kitchenham dataset whilst conclusion instability existed in the Desharnais dataset. ElasticNet was outperformed by DNN and as such it is not recommended to be used as a SEE benchmark model.",

keywords = "Conclusion Instability, Deep Neural Network, ElasticNet, Prediction model, Software Effort Estimation",

author = "Bosu, \{Michael Franklin\} and Solomon Mensah and Kwabena Bennin and Diab Abuaiadah",

year = "2018",

month = jul,

doi = "10.18293/SEKE2018-126",

language = "English",

isbn = "1891706446",

series = "Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering, SEKE",

publisher = "Knowledge Systems Institute Graduate School",

pages = "368--371",

booktitle = "SEKE 2018: Proceedings of the 30th International Conference on Software Engineering and Knowledge Engineering",

note = "The 30th International Conference on Software Engineering and Knowledge Engineering (SEKE 2018), SEKE 2018 ; Conference date: 01-07-2018 Through 03-07-2018",

url = "http://ksiresearchorg.ipage.com/seke/seke18.html, http://ksiresearchorg.ipage.com/seke/sekeproc.html",

}

Bosu, MF, Mensah, S , Bennin, K & Abuaiadah, D 2018, Revisiting the Conclusion Instability Issue in Software Effort Estimation. in SEKE 2018: Proceedings of the 30th International Conference on Software Engineering and Knowledge Engineering. Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering, SEKE, vol. 2018, Knowledge Systems Institute Graduate School, Pittsburgh, PA, pp. 368-371, The 30th International Conference on Software Engineering and Knowledge Engineering (SEKE 2018), Redwood City, United States, 1/07/18. https://doi.org/10.18293/SEKE2018-126

Revisiting the Conclusion Instability Issue in Software Effort Estimation. / Bosu, Michael Franklin; Mensah, Solomon ; Bennin, Kwabena et al.
SEKE 2018: Proceedings of the 30th International Conference on Software Engineering and Knowledge Engineering. Pittsburgh, PA: Knowledge Systems Institute Graduate School, 2018. p. 368-371 (Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering, SEKE; Vol. 2018).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Revisiting the Conclusion Instability Issue in Software Effort Estimation

AU - Bosu, Michael Franklin

AU - Mensah, Solomon

AU - Bennin, Kwabena

AU - Abuaiadah, Diab

PY - 2018/7

Y1 - 2018/7

N2 - Conclusion instability is the absence of observing the same effect under varying experimental conditions. Deep Neural Network (DNN) and ElasticNet software effort estimation (SEE) models were applied to two SEE datasets with the view of resolving the conclusion instability issue and assessing the suitability of ElasticNet as a viable SEE benchmark model. Results were mixed as both model types attain conclusion stability for the Kitchenham dataset whilst conclusion instability existed in the Desharnais dataset. ElasticNet was outperformed by DNN and as such it is not recommended to be used as a SEE benchmark model.

AB - Conclusion instability is the absence of observing the same effect under varying experimental conditions. Deep Neural Network (DNN) and ElasticNet software effort estimation (SEE) models were applied to two SEE datasets with the view of resolving the conclusion instability issue and assessing the suitability of ElasticNet as a viable SEE benchmark model. Results were mixed as both model types attain conclusion stability for the Kitchenham dataset whilst conclusion instability existed in the Desharnais dataset. ElasticNet was outperformed by DNN and as such it is not recommended to be used as a SEE benchmark model.

KW - Conclusion Instability

KW - Deep Neural Network

KW - ElasticNet

KW - Prediction model

KW - Software Effort Estimation

UR - https://www.scopus.com/pages/publications/85056862794

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85056862794&origin=recordpage

U2 - 10.18293/SEKE2018-126

DO - 10.18293/SEKE2018-126

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 1891706446

T3 - Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering, SEKE

SP - 368

EP - 371

BT - SEKE 2018: Proceedings of the 30th International Conference on Software Engineering and Knowledge Engineering

PB - Knowledge Systems Institute Graduate School

CY - Pittsburgh, PA

T2 - The 30th International Conference on Software Engineering and Knowledge Engineering (SEKE 2018)

Y2 - 1 July 2018 through 3 July 2018

ER -

Bosu MF, Mensah S , Bennin K, Abuaiadah D. Revisiting the Conclusion Instability Issue in Software Effort Estimation. In SEKE 2018: Proceedings of the 30th International Conference on Software Engineering and Knowledge Engineering. Pittsburgh, PA: Knowledge Systems Institute Graduate School. 2018. p. 368-371. (Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering, SEKE). doi: 10.18293/SEKE2018-126

Revisiting the Conclusion Instability Issue in Software Effort Estimation

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this