It is of great significance to analyze coupling coordination feature between urban spatial functional division (USFD) and green economic development for the realization of regional high-quality sustainable development. However, few studies have investigated the coupling between USFD and green economic development. Therefore, based on the analysis of the coupling and coordination mechanism between USFD and green development, this paper innovatively calculates the indicators of USFD and green economic development of 108 cities in the Yangtze River Economic Belt (YREB) from 2009 to 2019. Moreover, we explore the spatiotemporal patterns, evolution characteristics of the coupling degree between the USFD and green economic development using the improved entropy method, coupling model, kernel density estimation and spatial autocorrelation method, and further analyzes the influence factors with the Tobit regression method. The study found that: 1) During the study period, the development level of USFD and green economy in the YREB showed a fluctuating upward trend, but the development level was still low and there was a large space for improvement. 2) During the study period, the coupling coordination degree of USFD and green economy development in the YREB shows a favorable development trend of fluctuating growth, but it is still in the stage of moderate coupling and coordination development. The coupling degree shows a trend of polarization and the phenomenon of “high-value difference and low-value convergence” over time. 3) The spatial distribution of coupling coordination degree in each region is obviously different, and the middle and lower reaches are significantly higher than the upper reaches, and there are “club convergence” phenomenon and obvious H-H and L-L spatial agglomeration characteristics. 4) Technological innovation, industrial structure and physical capital have a significant positive impact on the coupling degree of the two systems, while human capital has a restraining effect on the growth of the coupling degree. There is heterogeneity in the extent and direction of the influence of each factor on the degree of coupling between the three agglomerations. These findings have significant policy implications for the region to facilitate rational division of labor and coordinated development of the green economy.

The coordinated promotion of urban digitalization and green development is an inevitable requirement for sustainable development in the digital age. Based on the coupling mechanism of urban digitalization and green development, in this study, we took 282 cities at the prefecture level and above in China from 2011 to 2019 as the research object, and we constructed the evaluation index system and calculated the coupling coordination degree (CD&GDD) of the two through the coupling coordination degree model. We further used the Dagum Gini coefficient, kernel density estimation, Markov chain and Moran’s I to assess the spatial effects of the regional differences, dynamic evolution trends and degree of coupling coordination. The results show the following: (1) The level of urban digitalization and green development show a fluctuating upward trend, and the interaction between the two is obvious. (2) Although the CD&GDD of most cities is continuously improving, it is still at a low level. There are large differences in the levels between the regions. (3) The inter-regional differences are the main source of the large overall differences in the CD&GDD in China, and these are mainly composed of the hypervariable density and net differences between the regions. (4) The phenomenon of “club convergence” exists in the CD&GDD. (5) The coupling coordination relationship between cities has a substantial spatial effect, and the spatial effect has obvious regional heterogeneity. The results and conclusions provide a reference for developing countries to promote green and low-carbon urban development.

This paper mainly uses support vector machine, random forest, logistic regression, and other machine learning algorithms to analyze the core data of listed companies, and then monitor their operating conditions and predict their bankruptcy probability. At the same time, the prediction effects of the three machine learning methods are evaluated by confusion matrix, ROC curve and other methods and indicators, and the best effect of the method is found. By predicting the bankruptcy probability of listed companies this study further supplements and improves the theory of machine learning algorithm on economic quantitative analysis.