Comparison of regression model, feed-forward neural network and radial basis neural network for software development effort estimation
Authors:
Open Access
- 30 September 2011
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGSOFT Software Engineering Notes
- Vol. 36 (5) , 1-5
Abstract
Accurate estimation of software development parameters such as effort, cost, and schedule is very important for effectively managing software development projects. Several software development effort estimation models have been developed in the last few decades. Determining, which is the best estimation model is difficult to decide for a software management team. In this paper we have compared Neural Network models and regression model for software development effort estimation. The comparison reveals that the Neural Network (NN) is better for effort prediction compared to regression analysis model. Further, we have compared two Neural Network models - Feed-Forward Neural Network (FFNN) and Radial Basis Neural Network (RBNN). The evaluation of the models is based on Mean Magnitude Relative Error (MMRE), Relative Standard Deviation (RSD) and Root Mean Squared Error (RMSE). The experimental results show that the RBNN model exhibits better prediction ability than FFNN.Keywords
This publication has 14 references indexed in Scilit:
- Probabilistic estimation of software size and effortExpert Systems with Applications, 2010
- Neural Network-A Novel Technique for Software Effort EstimationInternational Journal of Computer Theory and Engineering, 2010
- An empirical validation of a neural network model for software effort estimationExpert Systems with Applications, 2008
- An investigation of artificial neural networks based prediction systems in software project managementJournal of Systems and Software, 2008
- A comparison of software project overruns - flexible versus sequential development modelsIEEE Transactions on Software Engineering, 2005
- A simulation study of the model evaluation criterion mmreIEEE Transactions on Software Engineering, 2003
- Comparison of artificial neural network and regression models for estimating software development effortInformation and Software Technology, 2002
- A comparison of software effort estimation techniques: Using function points with neural networks, case-based reasoning and regression modelsJournal of Systems and Software, 1997
- Machine learning approaches to estimating software development effortIEEE Transactions on Software Engineering, 1995
- Software development cost estimation using function pointsIEEE Transactions on Software Engineering, 1994