Research on risk warning and control of engineering cost based on artificial intelligence

View at publisher Summarise with VIRAT
Authors: Weiyi Xu
Cited by: 0
References: 14

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

As engineering cost risk management becomes increasingly prominent in the construction industry, the application of artificial intelligence (AI) technology has become a key means to improve the efficiency of risk warning and control. This study aims to explore the application of AI technology in engineering cost risk management and propose corresponding warning and control strategies. Through literature review and case analysis, this study selected three models: Long Short-term Memory (LSTM) Network, Support Vector Machine (SVM), and Random Forest (RF), and compared their performance on Cost Variance Ratio (CVR), Schedule Performance Index (SPI), and Risk Response Efficiency (RRE) as key evaluation indicators. The research methods include data collection and preprocessing, model training and testing, and performance evaluation. The experimental results indicated that the minimum CVR of the LSTM model was 1.1%; the maximum SPI was 1.03; the risk response efficiency was as low as 12.5 minutes. The conclusion points out that LSTM can effectively improve engineering cost risk warning, providing a new perspective and technical support for project management in the construction industry.

Fields of Study & Subjects

Construction Project Management and Performance BIM and Construction Integration Economic and Technological Systems Analysis

Publication details

Journal / source
International Conference on Engineering Management, Computer Applications, and Supply Chain (EMCAS)
Pages
69–69
Publication date
1 April 2026
Language
EN