Using Artificial Neural Networks and Function Points to Estimate 4GL Software Development Effort

G.E. Wittig, G.R Finnic
1994 Australasian Journal of Information Systems  
Hie value of neural network modelling techniques in performing complicated pattern recognition and nonlinear estimation tasks has been demonstrated across an impressive spectrum of applications. Software development is a complex environment with many interrelated factors affecting development effort and productivity. Accurate forecasting has proved difficult since many of these interrelationships are not fully understood. An attempt to capture the significant attributes of the software
more » ... e software development environment to enable improved accuracy in forecasting of development effort is made using backpropagation artificial neural networks. The data for this study was gathered from commercial 4GL software development projects, across a large range of sizes. As is typical of software developments, the range in productivity and other development factors in the data set is also large, accentuating the estimation problem. Despite these difficulties the neural network model predictions were reasonably accurate in comparison with other published results, indicating the potential of the use of this approach.
doi:10.3127/ajis.v1i2.424 fatcat:wckdhse3jbcdtfg54jqtrf2xvi