Software Development Cost and Time Forecasting Using a High Performance Artificial Neural Network Model

Communications in computer and information sciencePublished 17 December 2010

Iman Attarzadeh, Siew Hock Ow

DOI10.1007/978-3-642-18129-0_4

Source URL

Citations20

SJR quartileQ4

SJR score0.18

SNIP0.24

TL;DR

The experimental results show that applying the desirable features of artificial neural networks on the algorithmic estimation model improves the accuracy of time and cost estimation and estimated effort can be very close to the actual effort.

Abstract

Nowadays, mature software companies are more interested to have a precise estimation of software metrics such as project time, cost, quality, and risk at the early stages of software development process. The ability to precisely estimate project time and costs by project managers is one of the essential tasks in software development activities, and it named software effort estimation. The estimated effort at the early stage of project development process is uncertain, vague, and often the least accurate. It is because that very little information is available at the beginning stage of project. Therefore, a reliable and precise effort estimation model is an ongoing challenge for project managers and software engineers. This research work proposes a novel soft computing model incorporating Constructive Cost Model (COCOMO) to improve the precision of software time and cost estimation. The proposed artificial neural network model has good generalisation, adaption capability, and it can be interpreted and validated by software engineers. The experimental results show that applying the desirable features of artificial neural networks on the algorithmic estimation model improves the accuracy of time and cost estimation and estimated effort can be very close to the actual effort.

Keywords

Computer Science

IEEE Transactions on Software EngineeringEstimating software project effort using analogies

965 Citations1997Martin Shepperd, C. Schofield

It is argued that estimation by analogy is a viable technique that, at the very least, can be used by project managers to complement current estimation techniques.

View PDF

IEEE Transactions on Software EngineeringA General Empirical Solution to the Macro Software Sizing and Estimating Problem

801 Citations1978Lawrence H. Putnam

Application software development has been an area of organizational effort that has not been amenable to the normal managerial and cost controls.

Journal of Systems and SoftwareA review of studies on expert estimation of software development effort

611 Citations2003Magne Jørgensen

An extensive review of studies related to expert estimation of software development effort suggests that expert estimation is the most frequently applied estimation strategy for software projects, that there is no substantial evidence in favour of use of estimation models, and that there are situations where the authors can expect expert estimates to be more accurate than formal estimation models.

Annals of Software EngineeringSoftware development cost estimation approaches — A survey

587 Citations2000Barry Boehm, Chris Abts +1 more

This paper summarizes several classes of software cost estimation models and techniques: parametric models, expertise‐based techniques, learning‐oriented techniques, dynamics‐based models, regression‐ based models, and composite‐Bayesian techniques for integrating expertise-based and regression-based models.

IEEE Transactions on Software EngineeringMachine learning approaches to estimating software development effort

478 Citations1995Kannan Srinivasan, Douglas Fisher

Two methods of machine learning are described, which are used to build estimators of software development effort from historical data, which indicate that these techniques are competitive with traditional estimators on one dataset, but also illustrate that these methods are sensitive to the data on which they are trained.

A review of software surveys on software effort estimation

398 Citations2004Kjetil Moløkken, Magne Jørgensen

Estimation knowledge is summarized through a review of surveys on software effort estimation that most projects (60-80%) encounter effort and/or schedule overruns and there is no evidence that formal estimation models lead to more accurate estimates.

IEEE SoftwareUsing neural networks in reliability prediction

270 Citations1992N. Karunanithi, Darrell Whitley +1 more

Results with actual testing and debugging data suggest that neural-network models are better at endpoint predictions than analytic models, and can be more accurate than some commonly used analytic models.

Empirical Software EngineeringFault Prediction Modeling for Software Quality Estimation: Comparing Commonly Used Techniques

128 Citations2003Taghi M. Khoshgoftaar, Naeem Seliya

This case study consists of software metrics collected over four releases of a very large telecommunications system and observes that for both average absolute and average relative errors, the CART-LAD model performs the best while the S-PLUS model is ranked sixth.

AJIS. Australasian journal of information systems/AJIS. Australian journal of information systems/Australian journal of information systemsUsing Artificial Neural Networks and Function Points to Estimate 4GL Software Development Effort

81 Citations1994G.E. Wittig, G.R Finnic

An attempt to capture the significant attributes of the software development environment to enable improved accuracy in forecasting of development effort is made using backpropagation artificial neural networks.

View PDF

Applied IntelligenceApplying fuzzy neural network to estimate software development effort

69 Citations2007Sun-Jen Huang, Nan‐Hsing Chiu

A fuzzy neural network (FNN) approach for embedding artificial neural network into fuzzy inference processes in order to derive the software effort estimates is proposed and demonstrated by using the 63 historical project data in the well-known COCOMO model.