A highway investment risk assessment method based on extreme learning machine

Abstract

Investment risk assessment refers to the scientific prediction and assessment of the risk factors that may exist in the project, and then provide the necessary auxiliary decision-making opinions for the implementation of the project. Due to the importance of risk prediction in the process of project implementation, how to carry out investment risk assessment more accurately has become a hot research topic in the scientific community. The main research object of this paper is the highway. At present, the risk assessment methods for highways mainly include questionnaire survey method, expert evaluation method, etc. However, these methods have large subjective errors and cannot deal with a large number of data. In view of the above problems, this paper uses the extreme learning machine to establish the investment risk assessment model, and uses the kernel function and PSO algorithm to optimize the model. Compared with the traditional risk assessment, as well as the SVM, BP neural network and other existing risk assessment methods, the model proposed in this paper has certain advantages in training time and other aspects. At the same time, it also compares the basic ELM, the ELM combined with the kernel function and the ELM combined with the PSO algorithm to predict the risk. The experimental results show that the addition of the kernel function and the PSO algorithm can alleviate the overfitting problem of the ELM model and improve the accuracy of risk prediction. Therefore, the investment risk assessment method based on extreme learning machine proposed in this paper can provide some auxiliary decision-making for highway investment projects in China.