Data categorization methods are used to assign class labels to the transactional data values. Resource requirement for the data categorization process is very high. In cloud environment users’ data are usually processed remotely in unknown machines that users do not own or operate. User data control is reduced on data sharing under remote machines. Anomalous and normal transactions are identified using classification techniques. Neural network techniques are used for the classification process. Back-Propagation Neural network (BPN) is an effective method for learning neural networks.