Comparison of Machine Learning Techniques for the Detection of the Electricity Theft

摘要

There are many applications available for detecting the electricity theft. However, only few studies compare the machine learning techniques in discovering electricity-stealing behavior. This study, therefore, compares the predictive accuracy of several machine learning methods including Logistic Regression (LR), The K-Nearest Neighbor Algorithm, (K-NN), Support Vector Machines (SVM), and Neural Networks (NNet) for predicting the electricity thefts in a concrete model.