International Journal of Soft Computing and Engineering (IJSCE)
In this paper, the authors examined the application of artificial neural network for software quality prediction using object-oriented metrics. Quality estimation includes estimating maintainability of software. In this paper, maintenance effort was chosen as the dependent variable and principal components of object-oriented metrics as the dependent variables. They are prediction the number of lines per changed per class. Two neural network models are used; they are ward neural network and Hopfield neural network. The artificial neural network possesses the advantages of predicting software quality accurately and identifies the defects by efficient discovery mechanisms.