Article Preview
TopThe subway plays a pivotal role in the urban rail transit system by connecting various regions and transportation networks within a city. This integration enhances transportation efficiency, convenience, and environmental protection, ultimately fostering the growth of the urban economy. Amidst the ongoing advancement of information technology, artificial intelligence has experienced rapid progress. Both domestic and international research communities are actively exploring the application of novel technologies and methodologies to aid in subway investment decisions.
Patel et al. (2018) delineated urban sustainable development into three dimensions: social, environmental, and economic sustainability. Within this framework, they specifically analyzed the comparative advantages of rail transit vis-à-vis traditional public transportation. Meanwhile, Bouteraa (2021) utilized fuzzy mathematical theory to develop an engineering investment prediction model, demonstrating swifter predictions when compared to conventional investment estimation techniques.
Chabane et al. (2019) grounded their research on investment decision support for subway infrastructure in the grid theory of railway infrastructure. They segmented long steel rail equipment into uniform small sections, forming the basis for their two-part study. Jae Yeol et al. (2018) harnessed computers to evaluate historical data from completed projects, scrutinizing investment control strategies for upcoming projects. Liu et al. (2020) tackled the discrete optimization problem between project duration and cost in multimodal scenarios. Through computer-aided analysis of historical data, they arrived at practical solutions.
Wang et al. (2021) provided a comprehensive overview of the current status of subway development both domestically and internationally, outlining the fundamental principles of subway investment. Utilizing data from a specific subway, they conducted relevant research on denoising and mileage correction. Pascual-Paach et al. (2021) integrated the earned value method with BIM technology in construction cost control, yielding favorable application outcomes. Jemal et al. (2019) addressed challenges in the dynamic control of engineering progress and cost by combining BIM technology with earned value analysis. They employed WBS task decomposition to analyze deviations between construction process cost and time, optimizing deviation adjustment measures through comparative analysis (Huang et al., 2023; Feng & Chen, 2022).
Furthermore, Wang et al. (2021) devised a regression equation model that utilizes regression analysis methods to predict construction investment based on extensive completed project data. Oliveira et al. (2020) investigated the optimal investment decision problem within the context of subsidy support policy switching, formulating a decision model to assist investors in making informed choices when subsidy policies change. Lastly, Naranjo and Santos (2019) uncovered a fuzzy system for stock market investment decision-making rooted in fuzzy candle pattern recognition, shedding light on potential applications in the investment domain.
The currently employed traditional investment estimation methods have been empirically shown to exhibit low accuracy in predicting investment values, leading to significant deviations from the actual investment in engineering construction. The emergence of DSS marks another milestone in information system research. DSS seamlessly integrates knowledge from various disciplines, including computer science, behavior, and AI. Through interdisciplinary analysis, it examines the extent to which computers contribute to management decision-making. The intelligent subway project investment DSS proposed in this article has the potential to substantially enhance the efficiency and accuracy of subway project investment decisions. This system offers robust support for subway construction and management, signifying a significant advancement in the field.