Software Development Effort Estimation - Neural Network Vs. Regression Modeling Approach
Roheet Bhatnagar, Vandana Bhattacharjee, M. K. Ghose · 2010
The global software development industry has now become more matured and complex. The industry is making use of newer tools and approaches of software development. The challenge then lies in accurately modeling and predicting the software development effort, and then create project development schedule. This work employs a neural network (NN) approach and a multiple regression modeling approach to model and predict the software development effort based on an available real life dataset which is prepared by Lopez-Martin et al. [1, 2]. A comparison between results obtained by both the approaches is presented. It is concluded that NN is able to successfully model the complex, non-linear relationship between a large number of effort drivers and the software maintenance effort, with results closely matching the effort estimated by experts.