Electricity stealing customer identification method and device

According to the electricity-stealing customer identification method and device provided by the invention, the comprehensiveness and accuracy of the to-be-identified data are improved by constructing the electricity-stealing customer index system, and the model with the best electricity-stealing customer identification effect in the identification model based on the LM neural network and the identification model based on the CART decision tree is used as the electricity-stealing customer identification model, so that the electricity-stealing customer identification efficiency is improved. The LM neural network has the local convergence of a Gaussian-Newton method and also has the global characteristics of a gradient descent method, the CART decision tree is high in efficiency, the maximum calculation times of each prediction do not exceed the depth of the decision tree, and the decision tree has no assumption requirement of statistical distribution on input data, so that the accuracy of the CART decision tree