Scholars have proposed a series of methods, such as “sustainability of local government debt”, to measure local government debt risks. However, these methods have caused a lot of controversy. Based on a macro balance sheet, this study uses an improved “distance to distress” to measure China’s local government debt risks and applies a social network model to identify the spatial correlation characteristics, as well as the spillover effect. The results are as follows: (1) The data show multiple and heterogeneous spatial correlations for China’s local government debt risks; (2) there are some similarities between the subgroups and seven major geographic regions in China. The links among subgroups are randomly distributed and external; (3) the data manifest a “small world”, with a decreasing transitivity since 2014; (4) between these two significant factors, the positive impact of local government competition is more obvious than the division of powers and responsibilities; and (5) the spatial spillover effect of China’s local government debt risks results from the combination of local government competition, the division of powers and responsibilities, and local government intervention. This paper provides a scientific basis for obtaining a deeper understanding of China’s local government debt risks, and puts forward policy recommendations to strengthen China’s debt management.

This paper aims to explore several ways to construct a scientific and comprehensive early warning system (EWS) for local government debt risk in China. In order to achieve this goal, this paper studies the local government debt risk from multiple perspectives, i.e., individual risk, contagion risk, static risk and dynamic risk. Firstly, taking China’s 30 provinces over the period of 2010~ 2018 as a sample, this paper establishes early warning indicators for individual risk of local government debt, and uses the network model to establish early warning indicators for contagion risk of local government debt. Then, this paper applies the criteria importance though intercrieria correlation (CRITIC) method and coefficient of variation method to obtain the proxy variable Ⅰ, which combines the above two risks. Secondly, based on the proxy variable Ⅰ, both the Markov-switching autoregressive (MS-AR) model and coefficient of variation method are used to obtain the proxy variable Ⅱ, which comprehensively considers the individual risk, contagion risk, static risk and dynamic risk of local government debt. Finally, machine learning algorithms are adopted to generalize the EWS designed in this paper. The results show that: (1) From different perspectives of local government debt risk, the list of provinces that require early warning is different; (2) The support vector machines can well generalize our EWS.