Research on the Model of Improving Engineering Safety Management Decision Support System Using Data Mining Technology

With the increasing scale and complexity of modern engineering projects, the challenges faced by engineering safety management are becoming increasingly severe. To address this problem, this paper proposes a model of engineering safety management decision support system based on data mining technology. The model uses advanced algorithms such as gradient boosting decision tree (GBDT) to extract valuable information from a large amount of engineering safety data to classify and predict potential risks. The system architecture consists of modules such as data preprocessing, risk identification, risk assessment and decision support, which can effectively improve the accuracy of risk identification. Through simulation tests on actual engineering project data sets, the risk prediction accuracy of the system model reached 92.5%, which is about 15% higher than that of traditional methods. In addition, the system shows good generalization ability in different engineering scenarios, reducing the impact of human factors on safety management decisions. Experimental results show that the system cannot only help engineering managers identify high-risk areas, but also provide optimized safety management decision suggestions, significantly improving the safety of engineering projects. The research in this paper shows that the data-driven engineering safety management model provides a new decision support means for the field of engineering management.