Fault-prone module prediction of a web application using artificial neural networks

The problem addressed in this research is the prediction of fault-prone modules in a web application using Artificial Neural Networks. Past research in this area focused on applications related to procedural paradigm and object-oriented paradigm. In this paper, we turned our attention to applying Artificial Neural Networks to fault module prediction of a web application. In our research, we implemented Principal Component Analysis technique and Error Back propagation training algorithm. The modules are classified into two classes- fault-prone and not fault-prone using web application quality metric data. The proposed model is based on supervised learning using Multilayer Perceptron Neural Network.