The prediction method of material consumption for electric power production based on PCBoost and SVM

Analysis of safety inventory decision is of great significance to effectively reduce the inventory cost and fund occupancy rate, and to ensure timely material supply of power grid, while analysis of safety inventory decision of power companies is based on material consumption forecasting data. As the industry particularity of power company material consumption, the existing problems of data are not balanced and short of quantity of the training set (small sample). To solve these two problems, this paper first proposed the use of improved PCBoost algorithm based on AdaBoost and combined with SVM (Support Vector Machine) to solve the unbalance and the small number in the training set, and the experimental results are revealed.