Predicting fraud in mobile phone usage using artificial neural networks

Mobile phone usage involves the use of wireless communication devices that can be carried anywhere, as they require no physical connection to any external wires to work. However, mobile technology is not without its own problems. Fraud is prevalent in both fixed and mobile networks of all technologies. Frauds have plagued the telecommunication industries, financial institutions and other organizations for a long time. The aim of this research work and research publication is to apply 3 different neural network models (Fuzzy, Radial Basis and the Feedforward) to the prediction of fraud in real-life data of phone usage and also analyze and evaluate their performances with respect to their predicting capability. From the analysis and model predictability experiment carried out in this scientific research work, it was discovered that the fuzzy network model had the minimum error generated in its fraud predicting capability. Thus, its performance in terms of the error generated in this fraud prediction experiment showed that its NMSE (Normalized mean squared error) for the fraud predicted was 1.98264609. The mean absolute error (M AE = 15.00987244) for its fraud prediction was also the least; this showed that the fuzzy model fraud predictability was much better than the other two models.