Software effort estimation using a neural network ensemble

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Accurate software effort estimation is crucial for software consulting organizations to stay competitive in their software development costs and retain customers. Artificial Neural Network (ANN) is an effective tool to obtain accurate effort estimates. In this paper, software effort estimation models using Artificial Neural Network (ANN) ensembles and regression analysis are developed based on data collected from 163 software development projects. The main emphasis of the paper is in developing an effective experimental design to achieve superior effort estimation results. In addition, we compare the software effort estimation of ANNs and multiple regression analysis. We found two interesting results. First, variables other than size (function points) are not especially helpful in predicting software development effort. Second, a properly designed ANN ensemble significantly outperforms estimation using regression analysis and can achieve better effort estimate predictions.

Original languageEnglish (US)
Pages (from-to)49-58
Number of pages10
JournalJournal of Computer Information Systems
Volume53
Issue number4
DOIs
StatePublished - Jan 1 2013

Fingerprint

neural network
Neural networks
software development
Regression analysis
Software engineering
regression analysis
management counsulting
Electric network analysis
network analysis
development project
Design of experiments
customer
software
costs
Costs

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Education
  • Computer Networks and Communications

Cite this

@article{c3e45169d49c4569b654d85efaba7ccb,
title = "Software effort estimation using a neural network ensemble",
abstract = "Accurate software effort estimation is crucial for software consulting organizations to stay competitive in their software development costs and retain customers. Artificial Neural Network (ANN) is an effective tool to obtain accurate effort estimates. In this paper, software effort estimation models using Artificial Neural Network (ANN) ensembles and regression analysis are developed based on data collected from 163 software development projects. The main emphasis of the paper is in developing an effective experimental design to achieve superior effort estimation results. In addition, we compare the software effort estimation of ANNs and multiple regression analysis. We found two interesting results. First, variables other than size (function points) are not especially helpful in predicting software development effort. Second, a properly designed ANN ensemble significantly outperforms estimation using regression analysis and can achieve better effort estimate predictions.",
author = "Pai, {Dinesh Ramdas} and McFall, {Kevin S.} and Girish Subramanian",
year = "2013",
month = "1",
day = "1",
doi = "10.1080/08874417.2013.11645650",
language = "English (US)",
volume = "53",
pages = "49--58",
journal = "Journal of Computer Information Systems",
issn = "0887-4417",
publisher = "International Association for Computer Information Systems",
number = "4",

}

Software effort estimation using a neural network ensemble. / Pai, Dinesh Ramdas; McFall, Kevin S.; Subramanian, Girish.

In: Journal of Computer Information Systems, Vol. 53, No. 4, 01.01.2013, p. 49-58.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Software effort estimation using a neural network ensemble

AU - Pai, Dinesh Ramdas

AU - McFall, Kevin S.

AU - Subramanian, Girish

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Accurate software effort estimation is crucial for software consulting organizations to stay competitive in their software development costs and retain customers. Artificial Neural Network (ANN) is an effective tool to obtain accurate effort estimates. In this paper, software effort estimation models using Artificial Neural Network (ANN) ensembles and regression analysis are developed based on data collected from 163 software development projects. The main emphasis of the paper is in developing an effective experimental design to achieve superior effort estimation results. In addition, we compare the software effort estimation of ANNs and multiple regression analysis. We found two interesting results. First, variables other than size (function points) are not especially helpful in predicting software development effort. Second, a properly designed ANN ensemble significantly outperforms estimation using regression analysis and can achieve better effort estimate predictions.

AB - Accurate software effort estimation is crucial for software consulting organizations to stay competitive in their software development costs and retain customers. Artificial Neural Network (ANN) is an effective tool to obtain accurate effort estimates. In this paper, software effort estimation models using Artificial Neural Network (ANN) ensembles and regression analysis are developed based on data collected from 163 software development projects. The main emphasis of the paper is in developing an effective experimental design to achieve superior effort estimation results. In addition, we compare the software effort estimation of ANNs and multiple regression analysis. We found two interesting results. First, variables other than size (function points) are not especially helpful in predicting software development effort. Second, a properly designed ANN ensemble significantly outperforms estimation using regression analysis and can achieve better effort estimate predictions.

UR - http://www.scopus.com/inward/record.url?scp=84882691460&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84882691460&partnerID=8YFLogxK

U2 - 10.1080/08874417.2013.11645650

DO - 10.1080/08874417.2013.11645650

M3 - Article

AN - SCOPUS:84882691460

VL - 53

SP - 49

EP - 58

JO - Journal of Computer Information Systems

JF - Journal of Computer Information Systems

SN - 0887-4417

IS - 4

ER -