During these days the number of electricity thieves are increasing, so that the
electricity boards are facing problems in providing electricity to their consumers in an
efficient way. In order to encounter these issue we need an accurate Electricity Theft
Detection (ETD) which is quite challenging due to the inaccurate classification on the
imbalance electricity consumption data, the overfitting issues and the High False
Positive Rate (FPR) of the previous techniques. To overcome the above limitations,
this paper presents a new model, which is mainly based on the supervised machine
learning techniques and real electricity consumption data.