Global Credit Research Articles

Credit Risk Prediction Using Machine Learning and Deep Learning: A Study on Credit Card Customers

The increasing population and emerging business opportunities have led to a rise in consumer spending. Consequently, global credit card companies, including banks and financial institutions, face the challenge of managing the associated credit risks. It is crucial for these institutions to accurately classify credit card customers as “good” or “bad” to minimize capital loss. This research investigates the approaches for predicting the default status of credit card customer via the application of various machine-learning models, including neural networks, logistic regression, AdaBoost, XGBoost, and LightGBM. Performance metrics such as accuracy, precision, recall, F1 score, ROC, and MCC for all these models are employed to compare the efficiency of the algorithms. The results indicate that XGBoost outperforms other models, achieving an accuracy of 99.4%. The outcomes from this study suggest that effective credit risk analysis would aid in informed lending decisions, and the application of machine-learning and deep-learning algorithms has significantly improved predictive accuracy in this domain.

Desire at play: Tourism, credit cards and the American Express Money Card travel board game

This article analyses the American Express travel board game Money Card (1972) as it highlights the intertwinement between the rise of a distinctive form of tourism as a modern mass industry and the expansion of the capitalist market, the primacy of the dollar, and U.S. hegemony. In a period marked by a shift from paper money to credit cards and global credit markets, American Express was the most powerful and easily identifiable symbol of the new post-war international economic order dominated by U.S. economic and political power. Placing the American Express Money Card board game within the shift from the post-war economy of reconstruction to credit expansion and neoliberalism, brings to the forefront the ways in which the game presented tourism as a ritual in celebration of capitalism. As a form of armchair travel, the board game sold tourism as a re-enchantment of the world. The article explores how the board game framed the American Express Card as fetish object, portrayed Europe as up for sale, and created a desire for the services of American Express and consumerism more generally. It shows how players were trained to use credit cards, be good consumers, and participate in the economy of the tourist industry. By advancing a capitalist tourist dreamworld, Money Card shaped perceptions of travel to Europe and created a religious illusion, offering a re-enchantment of the world through tourism and credit cards.

Which Global Cycle? A Stochastic Factor Selection Approach for Global Macro-Financial Cycles

Abstract Instead of assuming a certain factor structure, we statistically test for the factor structure driving common global dynamics in macroeconomic and financial data by employing a stochastic factor selection approach. Using a sample of 16 developed countries from 1996Q1 to 2019Q4, we present strong empirical evidence of a global macro-financial cycle and an independent global financial cycle. Moreover, the global macro-financial cycle we estimate is essentially the global business cycle identified in the literature. It captures the common global macroeconomic dynamics and drives a significant share of the comovement in the financial sector. The remaining commonality in financial variables is driven by separate global financial cycles: the global credit cycle and the global capital flow cycle.

Efficiency of Federated Learning and Blockchain in Preserving Privacy and Enhancing the Performance of Credit Card Fraud Detection (CCFD) Systems

Increasing global credit card usage has elevated it to a preferred payment method for daily transactions, underscoring its significance in global financial cybersecurity. This paper introduces a credit card fraud detection (CCFD) system that integrates federated learning (FL) with blockchain technology. The experiment employs FL to establish a global learning model on the cloud server, which transmits initial parameters to individual local learning models on fog nodes. With three banks (fog nodes) involved, each bank trains its learning model locally, ensuring data privacy, and subsequently sends back updated parameters to the global learning model. Through the integration of FL and blockchain, our system ensures privacy preservation and data protection. We utilize three machine learning and deep neural network learning algorithms, RF, CNN, and LSTM, alongside deep optimization techniques such as ADAM, SGD, and MSGD. The SMOTE oversampling technique is also employed to balance the dataset before model training. Our proposed framework has demonstrated efficiency and effectiveness in enhancing classification performance and prediction accuracy.

The role of Japanese corporate governance features in explaining rating differences between global and Japanese rating agencies

Many Japanese bond issuers believe that global credit rating agencies (CRAs)—Moody's and S&P—do not consider the unique corporate governance structure in Japan and assign lower credit ratings even though the “main bank” relationship in Japan can significantly reduce the default risk of these companies. Using 5,814 rated corporate bonds issued by 558 non-financial firms in Japan from 2003 to 2021, we find that local CRAs (R&I and JCR) weigh unique Japanese corporate governance features more heavily and assign higher ratings to Japanese corporate bonds relative to global CRAs. Our results further suggest that the degree of rating differences between local and global CRAs for individual issuers results from systematically different assessments of company-specific risk by these CRAs. Our data also reveal that the importance of main bank ties in Japanese corporate governance remains intact in more recent years, contrary to previous findings.

Reprint of “Unveiling the dance of commodity prices and the global financial cycle”

We examine the impact of commodity price changes on the business cycles and capital flows in emerging markets and developing economies (EMDEs), distinguishing between their role as a source of shock and as a channel of transmission of global shocks. Our findings reveal that surges in export prices, triggered by commodity price shocks, boost domestic GDP, an effect further amplified by the endogenous decline of country spreads. However, the effects on capital flows appear muted. Shifts in U.S. monetary policy and global risk appetite drive the global financial cycle in EMDEs. Eased global credit conditions, attributed to looser U.S. monetary policy or lower global risk appetite, lead to a rise in export prices, higher output, a decrease in government borrowing costs, and stimulate greater capital flows. The endogenous response of export prices amplifies the output effects of a more accommodative U.S. monetary policy while country spreads magnify the impact of shifts in global risk appetite.

Unveiling the dance of commodity prices and the global financial cycle

We examine the impact of commodity price changes on the business cycles and capital flows in emerging markets and developing economies (EMDEs), distinguishing between their role as a source of shock and as a channel of transmission of global shocks. Our findings reveal that surges in export prices, triggered by commodity price shocks, boost domestic GDP, an effect further amplified by the endogenous decline of country spreads. However, the effects on capital flows appear muted. Shifts in U.S. monetary policy and global risk appetite drive the global financial cycle in EMDEs. Eased global credit conditions, attributed to looser U.S. monetary policy or lower global risk appetite, lead to a rise in export prices, higher output, a decrease in government borrowing costs, and stimulate greater capital flows. The endogenous response of export prices amplifies the output effects of a more accommodative U.S. monetary policy while country spreads magnify the impact of shifts in global risk appetite.

Repression and growth in the periphery of Europe: The politics of changing growth regime in Turkey

This study shows that in peripheral economies that are linked into circuits of global capital on unequal terms, attempts to change the core features of an existing growth regime without broader political support intensify externally induced conflict among the ruling coalition. Under these circumstances, a transition to a new demand regime within a short time frame is more likely to take place via authoritarian intervention when the political cost of repression is lower than the cost of redistribution. In developing these points, the analysis builds on evidence from Turkey: following the 2008 global credit crunch, the Justice and Development Party’s (Adalet ve Kalkinma Partisi, AKP) domestic demand-led and credit-fueled growth under dependent financialization has experienced a major crisis. However, the subsequent push to replace this regime with a profit-led model with an emphasis on exports worsened the conflict among the political coalition supporting the party as their preferences over monetary policy began to diverge. A temporary resolution of this deepening rift has been possible by way of an authoritarian intervention under R. T. Erdogan’s presidential bid in 2017–18. By situating the debate on the relationship between growth regimes and political institutions, the study further unpacks the nexus between democratic backsliding, dominant social blocs, and economic growth in the periphery of Europe.

The Global Credit and Euro Area Financial shocks: How important are they for Albania?

The Global Credit and Euro Area Financial shocks: How important are they for Albania?

The global credit sector in the shadow of COVID19: financial assessment

The global credit sector in the shadow of COVID19: financial assessment

Assessing the Macroeconomic Consequences of External Financial Upheavals on China: A Caution of a Silicon Valley Bank’s Collapse

In the context of an increasingly interconnected global economy, deciphering the complex ripple effects of external financial disruptions on national economies is a task of utmost significance. This article dives deep into the intricate repercussions of such disturbances on the macroeconomic dynamics of China using the example of the potential insolvency of a Silicon Valley bank. Grounded in empirical scrutiny, we leverage data spanning from Q1 2000 to Q1 2022 and the analytical utility of the impulse response function to illuminate our findings. We find that external financial tumult triggers a global recession, adversely impacting China’s export-driven economy while simultaneously unsettling aggregate output, employment levels, and wage stability. Simultaneously, these disruptions induce variability in consumption tendencies, investment trajectories, and import volumes and inject instability into interest rate paradigms. We also acknowledge the potential for currency depreciation and bank insolvency incidents to induce inflationary stresses, primarily by escalating the costs of imports. However, these inflationary tendencies may be offset by the concomitant economic slowdown and diminished demand inherent to global recessions. Importantly, the tightening of global credit conditions, coupled with existing financial ambiguities, may obstruct investment initiatives, curtail imports, and exert influence on both risk-free and lending interest rates. Our investigation also probes into the response of the Chinese government’s monetary policy to these external financial shocks. Despite the vital role of monetary policy in alleviating the impacts of these shocks, the potential secondary effects on China’s domestic economy warrant attention. Our study underscores the imperative of proper policy design rooted in a profound understanding of the intricate economic interdependencies for effective management and mitigation of the potentially detrimental consequences of such financial upheavals on China’s macroeconomic resilience within the tapestry of a tightly knit global financial ecosystem.

American financial hegemony, global capital cycles, and the macroeconomic growth environment

AbstractGlobal financial cycles have become a growing concern for scholars and policymakers. Recent research has identified these cycles as originating in American markets, at least in part due to policy innovations in the United States. We articulate a previously unidentified, but powerful, mechanism that influence growth (and growth volatility) in the global economy: expansions in the American financial cycle disproportionately affect global credit conditions, leading to a higher incidence of gross capital inflow surges that subsequently create a boom‐bust growth dynamic in recipient economies. We evaluate this argument with an extensive empirical examination of 102 countries from 1975 to 2011 and find substantial support for the argument: US financial market developments produce capital flow cycles that challenge the ability of policymakers to stabilize their macroeconomies. We disaggregate capital flows and find that interbank lending plays a crucial role in driving these outcomes, with the results exhibiting a high degree of robustness to alternative specifications. Domestic policy tools alone may be insufficiently powerful to counteract volatility induced by these capital waves emanating from the core of the global financial system.

Lessons from outperformance in the Indian financial sector

AbstractWe examine predictions and outcomes for the Indian financial sector in the pandemic period to (i) build a case for re‐examining our understanding of the sector and (ii) improve risk perceptions and policy design. Reasons for outperformance include reforms that led to a better balance between discretion from public sector dominance and the excess volatility of market‐based systems. This diversity, as well as divergence of the Indian credit cycle from the global credit cycle, was protective given the sustained external risks. It put the sector in a position to support the domestic recovery, despite global quantitative tightening. Public sector banks contribute to diversity. Non‐bank financial companies reach the unbanked sectors and improve financial inclusion. Regulatory excesses and absence of liquidity support contributed to persistence of financial stress. Policy lessons are for countries to avoid policy over‐reaction, aim for diversity, different types of exposures, some uniformity in financial sector regulation, with the appropriate balance between discipline and support, in order to reduce risks. There are lessons from India's more broad‐based regulation for the narrow bank‐based regulation in advanced economies, which is increasing global financial fragilities and risks. The share of markets has risen so much there that diversity is falling.

Direct Lending Shadow Banking Risk: Consequences of Commercial Banks Retreatment from European Middle Market

The regional bank consolidation in the 1990 and the global financial crisis 2008-2009 reshaped the global credit market broadly. This paper analyzes potential direct lending risks based on the commercial banks retreatment from the European middle market loan segment. Fundamental characteristics of the private debt market development, like the intensified competition for deals, yield compression and deterioration of creditor protections and the potential shadow banking risks are analyzed. Furthermore, the lack of market information, delayed valuations and varying investment volumes are discussed in the context of challenging monitoring. In the conclusion the paper explains the importance for the European regulators to prepare for a drawdown of the private debt market, via three lines of defense to take care of the underwriting process, monitoring loans and restructuring expertise. Finally, the paper recommends conducting research on the European private debt deal structure and underlying investments for a regulatory monitoring.

The Global Credit Crisis of 2008: Causes and Responses

Since the COVID-19 pandemic began in 2018, the world has been suffering. Most obviously, the coronavirus killed millions of people and severely disrupted People's Daily lives. Beyond that, one of the most important effects is the enormous damage to the global economy. Unfortunately, 2021 saw the Russia-Ukraine incident, which seriously hurt the European economy and led to great challenges for the global economy. People grew less confident in the economy and began to hoard gold. In the process of global economic development, there have been many financial crises, the financial crisis in August 2008 is undoubtedly the biggest impact on the global financial market since 1929, and the impact is even worse than that of the Great Depression. The crisis was caused by a housing bubble and misleading economic policies such as the Federal Reserve's monetary policy, subprime mortgages, and CDS. Large financial institutions failed in droves, including Lehman Brothers. The causes and effects of the financial crisis are discussed in this article. The study concludes by discussing the significance of the issue and a variety of measures to stop such occurrences in the future. To ensure steady development of the global economy, especially in light of the ongoing effects of the COVID-19 epidemic and the conflict in Ukraine, this paper must draw lessons from the previous financial crisis and enhance government intervention of the financial system through policy adjustments.

In-Depth Analysis of the 2008 Financial Crisis

The financial crisis began in the 19th century. The international financial crisis has the remarkable characteristics of wide scope and great impact. Almost no nation in the world is untouched by the global financial crisis after it starts, and the losses incurred can take a long time to fully recover from and even continue to have an impact on the world economy. This paper chooses the most significant 2008 financial crisis as the study object and conducts a thorough analysis of it based on the basis in fact of the 2008 financial crisis brought on by the global financial crisis in the United States. The 2008 financial crisis was the worst crisis the world economy has encountered since the Great Depression of the 2030s. The global credit market and capital market have received an unprecedented and violent impact, and the economic development of many countries around the world has stagnated or even declined. By studying the causes, consequences and corresponding adjustments and changes of the 2008 financial crisis, we can grasp the international economic environment more scientifically and analyze the trend of world economic development after the financial crisis from a more targeted perspective.

Research on the Corporate Bond Risk Factors

The global bond market is greater than the global equity market meanwhile it grows gradually in recent years. Issuing corporate bonds is an ideal channel for enterprises to raise funds in the course of COVID-19 and also provides resilience in the market. Moody's, Standard & Poor's and Fitch are well-known global credit rating agencies and suggest investors purchasing investment-grade bonds for reasonable risks and returns. But local credit rating agencies have limited capacities to appraise local bonds. In the COVID-19 crisis, widen yield spreads represent likelihood of default which can be a measure of credit risk. Besides, government interventions (i.e., Quantitative Easing Program) can effectively eliminate credit risks and Confucian culture is a factor in assessing credit risks of corporate bonds. As for liquidity risk, Chinese bond market is less liquid than the US bond market and financial bonds are the most liquid in the Chinese market. The liquidity risk is caused by inaccurate information and market risk tolerance whereas market risk tolerance integrates credit and liquidity, the main measurement of liquidity risk is transaction cost which means that higher transaction cost can impede liquidity in the bond market. Finally, market risk comprises of COVID-19 pandemic, market design and biodiversity risk. The epidemic tightens the financial condition of developing countries and depreciates the currency of the bond market which raises term structure of interest rate up. A well-designed financial market system can help stabilize fluctuations during financial crisis. Besides, biodiversity risk is relevant to the operation apartment of companies.

Towards Better Banking Crisis Prediction: Could an Automatic Variable Selection Process Improve the Performance?*

This study proposes using the Least Absolute Shrinkage and Selection Operator (LASSO) method with cross‐validation to automate the variable selection process of the conventional multivariate logit early warning system (EWS), the purpose being to improve the prediction of systemic banking crises. Using a dataset covering 23 OECD countries with quarterly data from 1970Q1 to 2018Q3, model performance is evaluated in a recursive out‐of‐sample forecasting exercise, taking policy‐makers' preference of missed crises and false alarms into account. The results suggest that the automatic variable selection process can enhance the predictive performance of the EWS. It also highlights the importance of extracting information from variable interactions and lags that may not be easily identified and accessed by typical subjective variable pre‐selection. This simple approach is easy to interpret and is transparent, which are important aspects for effective policy communication. Five variables, namely credit growth, domestic and global credit gaps, real house price growth and the real effective exchange rate, are identified as the most important key indicators of systemic banking crises.

Cross-border credit networks, banking risk contagion and suppression effects

From the perspective of risk contagion, it is difficult to balance the benefits and costs of banking globalization. We use data on cross-border syndicated loans intended to build heterogeneous credit networks among banking sectors in various countries to explore the introduction of banking risks into the network. Via social network analysis (SNA), we find that the global credit network has phased characteristics, and it is a source of exposure to global banking risks. However, the more important network position, that is, the greater centrality, identified shows that the banking industry is more stable. To explain these findings, we present and estimate the banking risk contagion model and the suppression effect model of contagion. Evidence suggests that the international credit network is the channel of risk contagion, and the long-term loan network and nonfinancial borrower network have a stronger contagion effect. Exogenous banking supervision and network endogenous closeness centrality can inhibit risk contagion. From a policy perspective, these findings indicate the need to supervise high-risk cross-border loans and maintain independence in the international credit network. Data Availability StatementThe data that support the findings of this study are available from the corresponding author, [Heng Zhao, email: zhao0501@mail.dlut.edu.cn], upon reasonable request.

Why do banks use credit default swaps (CDS)? A systematic review

AbstractCredit default swaps (CDS)—the fiercely discussed derivatives instrument since the explosion of the recent global credit crunch—are still subject to considerable theoretical and practical debate. More than a decade after significant developments in CDS literature, we currently lack a holistic understanding of the disparate strands of evidence, synthesizing analytical advancements in the field. We, therefore, conducted a systematic review of 143 publications (peer‐reviewed and first‐tier grey literature), focusing on three key areas: CDS characteristics and development, credit risk hedging, and determinants of CDS use, and performed the first bibliometric mapping for CDS. Our review makes the following contributions. First, measuring CDS characteristics and development gives a snapshot of how CDS remained a significant indicator for hedging corporate lending risk. Second, by mapping the research landscape, we provide insights into banks’ use of CDS; in particular, we show that banks use CDS to obtain capital relief, enhance liquidity and profitability, limit credit supply, and consequently mitigate their NPLs’ level. Moreover, the use of CDS by lenders increases firms’ leverage and value. Leaving a fertile area for debates and future research, the outcomes of this review help provide policy guidance to regulators and financial institutions that make informed decisions to use CDS as a credit risk management instrument.