Abstract
In order to apply the random forest regression algorithm to the structural optimization of concrete frames, this paper uses the relative dynamic elastic modulus as the evaluation index of the concrete frame structure, and uses random forest feature selection based on the original samples to evaluate the importance of influencing factors and select variables. Based on the set of optimal influencing factors, a new method for optimizing the concrete frame structure of random forest based on genetic algorithm is proposed. High-quality decision trees are selected to join the genetic algorithm to reduce the scale of random forest and improve the classification accuracy. And can better improve the genetic algorithm of the concrete frame of random forest. The results show that compared with other models, the random forest model has the highest prediction accuracy and the best fitting effect. The proposed random forest prediction model has broad application prospects in the study of concrete frame structures. The random forest prediction model has the smallest error and the highest accuracy, which verifies the accuracy and reliability of the model. The proposed random forest prediction model provides an effective method for the prediction of concrete frame structures.