This study focuses on the core economic zone of East China, utilizing the decoupling model to investigate the relationship between carbon emissions and economic development in the construction industry. Furthermore, it analyzes the driving factors through the application of the logarithmic mean index method. The findings reveal that, firstly, Zhejiang and Jiangsu provinces exhibit higher total carbon emissions in the construction industry. Except for Fujian Province, the other regions exhibit a downward trend after 2019. Secondly, there is considerable spatial variability in carbon emissions in the construction industry within the core economic zone of East China, and it gradually decreases over the study period. While economically developed regions like Zhejiang and Jiangsu provinces tend to concentrate and consume more resources and energy, their impact on surrounding neighboring provinces or cities is relatively limited. Thirdly, carbon emissions from the construction industry in the core economic zone of East China show a development trend shifting from weak decoupling to strong decoupling, indicating a healthy growth in the construction industry. Specifically, different regions show different trends. Lastly, regarding influencing factors, the impact direction of carbon intensity on total carbon emissions shows instability. Energy intensity consistently exhibits inhibitory effects, and the economy and the population scale act as driving forces.

With the increasing trend of office buildings towards high-rise, multifunctional, and structurally complex architecture, the difficulty of engineering cost management has increased. Accurately estimating costs during the decision-making stage is crucial for ensuring the overall project’s financial viability. Therefore, finding straightforward and efficient methods for cost estimation is essential. This paper explores the application of algorithm-optimized back propagation neural networks and support vector machines in predicting the costs of office buildings. By employing grey relational analysis and principal component analysis to simplify indicators, six prediction models are developed: BPNN, GA-BPNN, PSO-BPNN, GA-SVM, PSO-SVM, and GSA-SVM models. After considering accuracy, stability, and computation time, the PCA-GSA-SVM model is identified as the most suitable for office building cost prediction. It achieves stable and rapid results, with an average mean square error of 0.024, a squared correlation coefficient of 0.927, and an average percentage error of 5.52% in experiments. Thus, the model proposed in this paper is both practical and reliable, offering valuable insights for decision-making in office building projects.