Detection of subscription fraud in telecommunications using decision tree learning
Abstract
Subscription fraud and bad debts are the major causes of loss of revenue in the telecommunication industry. This research project therefore, focused on designing a subscription fraud detection system with minimum false positive alerts using decision tree learning. The system has been trained to learn from training data and used decision tree algorithms to make classifications/predictions on future telecommunication data. Weka software was used to induce the resulting decision tree from the training data. The resulting decision tree was pruned and the pruned tree converted to rules which was implemented using Hypertext preprocessed (PHP) programming language, and the result was high detection rate with false positive rate kept very low (about 0.5005%).