Research on Cost Forecasting Based on the BIM and Neural Network

Abstract

In enterprise or project management, cost forecasting is an important factor affecting different stages of the project process, which requires effective control and management of cost forecasting. In this paper, BIM technology is introduced into the construction project, so that the project manager can master all the information of the building through this technology, which provides a good condition for the completion of cost accounting. In this paper, a cost prediction model based on a neural network is proposed, which uses a neural network prediction model, genetic algorithm prediction model, and GM (1, 1) prediction model. Through the same design company, the monthly cumulative cost of the construction and completion of the first, second, and third floors of the residential district is predicted. The results show that the error of the neural network model is small, while the error of the genetic algorithm and GM prediction model is large and unstable, which cannot provide more accurate and stable prediction, and has no better reference value. Therefore, we can see that the neural network prediction model has a good reference value, can provide accurate and stable prediction, and can help enterprises or project managers to make cost decisions.