Comprehensive evaluation of distribution network project cost management level based on optimized random forest

In this article, by analyzing the content and characteristics of cost management distribution network project, evaluation index system level is formulated first. Gini in random forest algorithm analytic hierarchy process are used to analyze influencing factors project from quantitative qualitative aspects. The results show that design change on-site visa have a great impact on level, while advance payment has relatively small impact. Based above analysis results, article simplifies indicators, so as optimize model. After verification, optimized model can improve efficiency evaluation, other hand, it effectively accuracy ensure scientificity provide reference for improving project.