Electric energy substitution potential prediction method and system based on random forest, storage medium and computer equipment

The invention discloses an electric energy substitution potential prediction method and system based on a random forest, a storage medium and computer equipment, capable of accurately identifying customers with high electric energy substitution potential of a power enterprise and providing data support for power marketing and customer service departments to carry out precision marketing and differentiated services. The electric energy substitution potential prediction method comprises the following steps: acquiring data to obtain a data source for predicting the electric energy substitution potential; extracting key features of the electric energy substitution potential customers, and constructing an index system of an electric energy substitution potential prediction model; extracting data according to industry fields, independently constructing a prediction model, extracting target customer and non-target customer data, and dividing into a training set, a verification set and a testset; preprocessing the da