MACHINE LEARNING METHODS FOR SYSTEMIC RISK ANALYSIS IN FINANCIAL SECTORS

Financial systemic risk – defined as the risk of collapse of an entire financial system vis-a-vis any one individual financial institution – is making inroads into academic research in the aftermath of the late 2000s Global Financial Crisis. We shed light on this new concept by investigating the value of various systemic financial risk measures in the corporate failure predictions of listed nonfinancial firms. Our sample includes 225,813 firm-quarter observations covering 8,604 US firms from 2000 Q1 to 2016 Q4. We find that financial systemic risk is incrementally useful in forecasting corporate failure over and above the predictions of the traditional accounting-based and market-based factors. Our results are stronger when the firm in consideration has higher equity volatility relative to financial sector volatility, the smaller size relative to the market, and more debts in current liabilities. The combined evidence suggests that systemic risk is a useful supplementary source of information in capital markets.

The characteristics of the new dual-cycle development pattern and systemic financial risk based on TVP-SVAR and MS-VAR model analyses

Financial systemic risk measurement based on causal network connectedness analysis

Local government debt plays an important role in promoting economic development, but with the continuous expansion of the scale of local government debt, coupled with the opacity of financial and debt information, local debt risk may be directly transformed into financial risk. Therefore, the potential mechanism of local government debt risk inducing systemic financial risk is studied to strictly control local government debt and prevent it at present. It is of great practical significance to mitigate systemic financial risk. At present, the research on local government debt mainly focuses on the mechanism of local government debt to amplify economic fluctuations, while the potential mechanism of local government debt risk to induce systemic financial risk is relatively few. From the perspective of local government bonds and land finance, the innovation of this paper is to depict the Chinese elements such as the maturity of local government bonds, the opacity of debt and financial information, and to integrate local government debt, land finance and financial intermediaries into the framework of general equilibrium to analyze the potential mechanism of systemic financial risk induced by local debt risk. This study finds that when the economy is facing negative productivity shocks, the decline in total output will inhibit the land demand of households and enterprises, and the decline in land prices caused by the decline in demand will reduce the land-related fiscal revenue of local governments. On the one hand, the decline of land-related fiscal revenue will reduce government expenditure; on the other hand, it will increase the pressure on local governments to repay debt and the risk of debt, which will lead to the rise of bond interest rates and the decline of bond prices. Lower bond prices will affect the balance sheet of financial intermediaries, resulting in increased leverage and risk premium of financial intermediaries. Under the balance sheet constraints, financial intermediaries will shrink corporate credit, resulting in an increase in systemic financial risk. Rising interest rates and tightening credit will restrain enterprises’ investment and land demand, further reduce total output and land prices, increase the debt risk of local governments, and form a financial accelerator mechanism in the economy, which will lead to the mutual reinforcement of the debt risk and financial risk of local governments and form a vicious circle. In addition, when financial risk rises, the default risk of local government debt is lower. Based on the trade-off between risk and return, financial intermediaries will hold more local government bonds. Credit squeeze brought by asset allocation changes will further strengthen the financial accelerator mechanism and strengthen the interaction between debt risk and financial risk. Meanwhile, although extending the bond maturity can reduce the pressure of local governments to repay their debt in the short term, the longer the bond maturity is, the greater the financial shock and economic volatility caused by local government debt risk are. The paper indicates that: for resolving local government debt risk and reducing the probability of systemic risk, we firstly need to improve the local government bond market, diversify local government bond investors, and change the current situation dominated by commercial banks; secondly, we should strengthen budget constraints and control the scale of local government debt; thirdly, we should rationally design the maturity structure of local government bonds, strengthen the transparency of local government finance and debt information, and play the role of market constraints; finally, when financial risk rises, the central bank can adopt non-traditional monetary policy to intervene in the market, which can reduce financial risk and social welfare losses.

As climate issues gain increasing attention, climate‐related risks now appear to have the potential to be transmitted to the financial system. This paper utilizes a bootstrap rolling window Granger causality test to explore the dynamic correlation between climate transition risk (CTR), climate physical risk (CPR), and financial systemic risk. Empirical findings reveal that, during periods of intensive climate policy transformation, CTR exhibits a significant enhancing effect on systemic financial risk. However, no such phenomenon is observed for CPR. This research indicates that the uncertainty brought about by transitions in climate policy can significantly influence financial systemic risk.

This dissertation consists of four essays, focusing on the relationship between financial risks, financial market uncertainty and macroeconomic conditions. The first essay estimates the effects of anticipated and unanticipated monetary policy changes on jump variation by employing high frequency non-parametric jump detection methods. We use an event study approach and a structural VAR framework in examining stock price jump variation for the aggregate economy, the financial, health, energy and telecommunication-information technology sectors (Tel-Info). We find that anticipated changes in the Fed funds have no significant effect on jumps. In contrast, jump variation in the price of financial market data increases with monetary policy surprises. We document evidence of asymmetries in the response of jumps to monetary policy changes. Monetary policy surprises and positive changes in the Fed target rate induce increment in jumps. Similar results exist in the sector analysis. In addition, this study uncovers no evidence of endogenous response between jumps and monetary policy surprises. The second essay estimates the response of uncertainty/risk aversion to monetary policy actions in both the financial sector and the aggregate economy using a Structural Vector Autoregressive (SVAR) model. When compared with other sectors, our constructs reveal that financial risk aversion/uncertainty has greater correlation with the aggregate risk aversion and uncertainty. Our analysis reveals that financial risk aversion and uncertainty exhibit stronger interdependence with monetary policy actions than aggregate uncertainty and risk aversion. The third essay provides the dynamic characterization of the link between ex-ante financial distress risk and the real economy. Using 219, 990 firm-year observations, an ex-ante measure of financial distress is generated at sector level. By employing simultaneous equation model, we provide a comprehensive set-up for predicting ex-ante financial distress risk and examining its effect on GDP growth. Over the period of 1970-2012, the results from the US firms reveal that ex-ante financial distress strongly relate to GDP growth. Ex-ante distress risk contracts GDP growth by up to 10%. Similar contractions in the growth of GDP are uncovered when a single equation approach is used in establishing the relationship between financial distress and growth in GDP. In addition, the results remain consistent when a confirmatory analysis is generated by using a weighted sector index of financial distress. The fourth essay examines liquidity risk and financial integration using bank level flows for 95 countries. The results suggest that global banking network influences liquidity risk. The more the banks are connected to each other the more they are prone to liquidity risk and the result is the same for intermediaries in the network formation. Borrowers that connect to important lenders are not at an advantage, but banks that have independent access to finance in the financial network are at an advantage. On a regional basis, banks in Europe, Africa and Asia and Pacific that have strong connections are prone to liquidity risk. American banks that function as intermediary in the network are prone to liquidity risk. Banks in the American region that have independent access to financing in the financial network are able to reduce liquidity creation, but their degree of connectivity worsens net stable funding.

Capital account liberalisation can give rise to uncertainty in capital flows, which may lead to an accumulation of financial risks. This study measures the systemic financial risk indices using the coefficient of variation method with data of 24 countries from 2003 to 2019 and the impact of capital account liberalisation on systemic financial risks using the panel threshold model. Evidence shows that systemic financial risk indices vary heterogeneously across countries. The systemic financial risk indices of high-income countries are lower than those of middle- and low-income countries. Second, capital account liberalisation has an asymmetric effect on systemic financial risk with a double threshold. Low-intensity and high-intensity capital account liberalisation increases systemic financial risk. However, medium-intensity capital account liberalisation is effective in reducing systemic financial risk. Third, the heterogeneity results suggest that capital account liberalisation is conducive to reducing the financial risk of high- and middle-income countries and has the opposite effect on low-income countries. Therefore, this study recommends that countries adjust the intensity of capital account liberalisation according to their national conditions. It is necessary to establish a regulatory system for cross-border capital flows and maximise the benefits of liberalisation while safeguarding financial market stability.

This paper uses communication network optimization algorithms to study financial market evolution and systemic risk warning. The Dijkstra algorithm optimizes the financial market network. Data processing like noise reduction improves risk analysis accuracy. The research focuses on systemic financial risks, covering their definition, measurement, warning mechanisms, and complex network model applications. A complex financial network framework is built. Methods such as optimal threshold determination and community detection are used to analyze market network characteristics in pre - pandemic, pandemic, and post - pandemic stages. The minimum spanning tree retains key risk paths, with optimal thresholds of 0.55, 0.62, and 0.67 for each stage. Community detection by the Fast - Newman algorithm shows pandemic impacts on financial market industry interconnections. Findings show pre - pandemic, the market was well - connected and stable. During the pandemic, connections weakened and risk isolation rose. Post - pandemic, the market recovered but not fully. Network topology indicators serve as risk warning metrics, with a 25% fluctuation threshold for early warnings. This research offers new ways to understand market vulnerabilities, optimize risk management, and forecast market trends during crises. The use of optimization algorithms and self - healing mechanisms in risk warning has great theoretical and practical value.

Non-alternative Collective Investment Schemes, Connectedness and Systemic Risk

Non-Alternative Collective Investment Schemes Connectedness and Systemic Risk

This paper contributes to the finance literature by investigating the risk contagion and bailout effects in the global financial system. We use the bilateral exposure matrix to examine the impact of credit shocks and liquidity shocks on the global financial system when a Global Systemically Important Bank (G-SIB) is supposed to be in distress. The findings indicate that the global financial network is dominated by large and medium-sized financial institutions. Credit shocks does not play a significant role in risk contagion nor do they trigger the systemic risk in the global financial system. However, the global financial network is more vulnerable to liquidity shocks than to credit shocks. If a credit shock and liquidity shock overlaps with each other, the hybrid shock can exacerbate the risk contagion effects and lead to rapid propagation throughout the global financial network. If a regulator bails out the distressed institutions, the bailout efficiency increases with the number of rescued institutions. However, the improvement in of bailout efficiency decreases with the number of rescued institutions. If a regulator can promote financial institutions to raise the rollover ratio, the financial system will be more robust to shocks. This paper provides a ground view of systemic risks contagion and sheds light on directions for future research on systemic risk contagion in the global financial system. • The credit shock does not play a significant role in risk contagion in the global financial system. However, the liquidity shock has shown more substantial effects than that of the credit shock. • If the credit shock and liquidity shock overlaps with each other, the contagion effects are amplified. • If the regulator implements the bailout, the total rescue effects in the second round is better than that of other rounds. • If the financial institutions can raise the rollover ratio, the impact of systemic risk could be reduced significantly.

Finance is becoming more important in the national economy. Maintaining financial stability is critical not only for the financial industry’s prosperity and development, but also for a country’s political, economic, and social development. This paper will look at the mechanisms that cause systemic risk to develop and evolve, as well as how to measure systemic financial risk in multiple dimensions. To begin, create a system for evaluating financial risk in a systematic manner. Second, using the AHP and CRITIC methods to determine various indicators and market weights, create a systemic financial risk evaluation model based on the system dynamics model, and calculate the system from 2010 to 2019 comprehensive financial risk index. Finally, simulation research is conducted using the system dynamics model of systemic financial risk, and the simulation results are analyzed. The findings show that China’s financial risk has been gradually increasing since 2016, with relatively small fluctuations in risk state.

It is an essential demand to establish an effective financial risk early-warning system for financial security. But some factors have a lagging effect on financial risk. So this paper aims to construct a reasonable and practical indicator system for financial risk early-warning. First, determine the explained variables of the indicator made up by Chinese financial stress index. Second, confirm the explanatory variables consisting of the macroeconomic variable, the currency credit variable, asset price variable and the macroeconomic variable of correlative economic powers. Finally, propose an optimum forecast equation to predict financial systemic risk status. In conclusion, the forecast outcomes indicate that Chinese financial systemic risk is on rising trend in the past three quarters in 2011 and higher than the peak of 2008, whereas financial systemic risk declines at the fourth quarter.

This paper documents research analysing the effects of the Maritime Transportation Security Act (MTSA) on a set of marine operator stocks listed on Nasdaq and the New York Stock Exchange (NYSE). The paper investigates whether MTSA resulted in a structural change in systematic risk for these companies. The paper conducted event studies using the market model to estimate the effect of MTSA on systematic risk. The empirical evidence shows that MTSA resulted in a structural reduction in systematic financial risk. These results had positive implications for the cost of these operators in raising capital. The results also show a substantial reduction in idiosyncratic risk and conditional systematic risk following MTSA which had a positive effect on market risk and liquidity. As a whole, MTSA was able to mitigate some of the increased financial risk associated with 9/11 for marine operators. From a policy standpoint, MTSA provided ancillary economic benefits by reducing these risks.

In recent years, local governments have boosted their local economies by raising large amounts of debt. Even though the state further strictly controls local government debt, the hidden debt formed by the local government borrowing in disguised form can infect systemic financial risks, creating an urgent need to carry out risk warning based on local government hidden debt. The paper uses the macro indicators of local government implicit debt risk at the prefecture-level city level, and introduces the micro indicators of PPP projects, financing platform bank debt, and urban investment debt to establish a BP neural network model. We not only study the contagion effect of local government hidden debt on systemic financial risks, but also predict the systemic financial risks in 2019 and construct an early warning risk system based on the prefecture-level city data from 2015 to 2018. In addition, the early warning effect of local government implicit debt on systemic financial risk under different stress scenarios is investigated. The study found that the implicit debt risk of local governments, the scale of financing platform bank debt, the scale of PPP, and the scale of urban investment bonds have a significant impact on systemic financial risks. The neural network model constructed by introducing these four variables at the same time can better predict the level of systemic financial risk. The model can also accurately predict the changes in systemic financial risks under the stress test of the increase in hidden debt of different local governments, and has a good early warning effect.