A comparative analysis of different neural networks performances in the prediction of superimposed fraud in mobile phone usage

Neural Networks is an essential information-processing paradigm,that is inspired by a way of biological nervous systems, which can be used in predicting fraud occurrence in mobile phone usage. Superimposed fraud occurrence could occur as a result of overlapping calls and irregularities in the time pattern spent in calling. The power of neural network-based technology is a potent mechanism in combating the menace of superimposed fraud in mobile technology. The methodology employed in this research work included data collection by survey from a telecommunication industry in Africa, data testing and analysis by making use of a Neural Network Software known as NeuroSolutions. Performance comparative analysis was carried out by using six different neural network models. The final deductions from the results of the experiments carried out, showed that the Fuzzy network model outperformed the other five neural networks in terms of the least error difference generated between the predicted output and the final output generated. This showed that Fuzzy network model is more efficient in its performance in comparison with the other five models.