A Data Mining based Model for Identifying of Spurious Behaviour in Water Utilization

Spurious(dishonourable) behaviour in drinking water utilization is a compelling problem facing water supplying companies and agencies. This behaviour results in a enormous loss of income and forms the highest percentage of non-technical loss. Finding competent analysis for identifying spurious activities has been an active research area in recent years. Intelligent data mining techniques can service water supplying companies to detect these spurious activities to decrease such losses. This analysis explores the use of two distribution techniques (SVM and KNN) to identify suspicious cheat water customers. The main encouragement of this analysis is to benefit Yarmouk Water Company (YWC) in Irbid city of Jordan to affect its profit loss. The SVM based approach uses customer load profile characteristics to display anomalous behaviour that is well-known to be interacted with non-technical loss activities. The data has been collected from the ancient data of the company billing system. The efficiency of the developed model hit a rate of over 74% which is better than the present standard prediction steps taken by the YWC. To expand the model, a opinion tool has been built using the develop model. The system will help the company to predict careful water customers to be authorized on site.