Landslides claim more than 4,000 lives annually and lead to approximately US$20 billion in economic losses. However, landslide hazard, risk assessment, and early warning systems remain constrained by fragmented, inconsistent, and incomplete data. This study addresses the global data gap by...

The rapid expansion of small and medium enterprise (SME) lending has intensified the need for accurate and interpretable credit risk forecasting. Financial institutions must anticipate potential business loan delinquency to maintain portfolio stability and meet regulatory standards. This study...

Financial risk early warning systems are essential for proactive risk management in volatile markets, particularly for emerging economies such as China. This study develops a hybrid deep learning model integrating Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Gated...

Purpose This study aims to develop a hybrid Early Warning System (EWS) that integrates the traditional Z-score method with machine learning algorithms to accurately predict the financial performance and potential failure of IRB in Indonesia. Design/methodology/approach The study employs a data...

This paper applies an empirical model of corporate capital structure, optimal debt, and overleveraging to estimate overleveraging measured as the difference between actual and optimal debt. Estimated using a sample of the twenty largest pharmaceutical firms, covering the time span from 2000 to...

This paper develops an early warning system for predicting distress for large European banks. Using a novel definition of distress derived from banks' headroom above regulatory requirements, we investigate the performance of three machine learning techniques against the traditional logistic...

This study presents a novel Early Warning System for monitoring the credit risk of commercial customers at a large international bank headquartered in the Netherlands. Traditional early warning methods often rely on backward-looking indicators such as probability of default or loss given...

The withdrawal of public sector intervention from Malta's housing market commenced in the early 1990s, while financial markets were liberalised in 1994. These developments were likely behind the significant expansion in credit and house price appreciation experienced over the past two decades,...

The workshop "The Future of Conflict Early Warning: New Technologies and Policy Impact" explored advancements in AI, data analytics, and their applications in conflict prevention. Key conclusions include the need for collaboration between policymakers and researchers to develop practical tools...

This study leverages the Log-Periodic Power Law Singularity (LPPLS) confidence indicator to effectively identify bubbles in agricultural commodity markets. We analyze five major grain price indices reported by the International Grains Council (IGC) from January 2000 to April 2023, successfully...

In November 2024, the value of certain crypto-assets has significantly and suddenly increased, hitting new records. This reflects an intensifying interest in relation to crypto-assets and confirms their highly volatile nature. ESMA is cautioning investors against being caught up in this hype....

It is now a well-known fact that climate is changing globally at an unprecedented rate and agriculture is one of the most vulnerable sectors to this change. Considered as a significant threat for food security, climate change and its impact on agricultural practices are among the most prominent...

This paper attempts to develop a framework for implementing the Countercyclical Capital Buffer (CCyB) in Mongolia's banking sector by identifying early warning indicators of systemic risk and examining the impact of capital adequacy on bank lending. Using quarterly data from 2000 to 2024, the...

This technical note (TN) focuses on the euro area (EA) banking sector, which has weathered a succession of shocks over the past few years with notable resilience. Strong starting capital positions, ample liquidity and a diversified deposit base allowed banks to absorb the effects of the COVID-19...

This paper introduces a novel application of Growth-at-Risk (GaR) as an early warning system (EWS) for predicting recessions. By transforming GaR into a classification model, we assess its ability to signal economic downturns across 11 Central and Eastern European (CEE) economies from 2005 to...

Amidst the constraints of carbon peaking and carbon neutrality goals (dual carbon) and high import dependence, safeguarding China's petroleum security faces intensified challenges. This study constructs a dynamic weight evaluation framework integrating four dimensions: "Availability",...

This study predicts bankruptcy among Indian firms using artificial intelligence-machine learning (AI-ML) methods, demonstrating their superior performance over traditional statistical models. Addressing class imbalance through oversampling techniques such as the synthetic minority oversampling...

This Brief analyses the EU warning system's contribution to conflict prevention and discusses ways to strengthen it. The first section examines the factors that contribute to the success of the system. The second section suggests how the system and the EU's overall prevention approach can be...

This report is one of the joint deliverables of Joint Research Centre on "Enhanced Situational Awareness for Crisis Management". It focuses on advancing towards integrated mid-term early warning system that will aim at anticipating disasters and crises within a 6-month window. Ability to detect...

This paper presents a technical note on bank stress testing and climate risks analysis in Maldives. Although the Maldives' economy has rebounded strongly from the pandemic-induced contraction, macro and financial vulnerabilities remain. The stress test results broadly corroborated the identified...

Abrupt changes are a prevalent feature of financial data sets, such as prices of financial assets, returns of stocks, exchange rates, etc. An early warning system (EWS) can detect existing changes and predict possible future changes before they occur. Two important statistical models for change...

This study utilizes machine learning models, including Logistic Regression, Support Vector Machine, Decision Tree, and Random Forest, in the early warning system for debt group migration in a Vietnamese commercial bank. In predicting customers' overdue debt migration (B Score), the RF model...

The main contribution of this paper is the construction of a cyclical systemic risk indicator from early warning indicators of banking crises (EWIs) used in Finland. Previous research has shown that combining EWIs can enhance their early warning properties. This study evaluates the indicator's...

Early warning signals (EWS) of imminent regime shifts can be identified through the observation of a system's behavior under increasing stress and before crossing a tipping point. Despite many advances in the detection of EWS in recent years, EWS are yet to find direct application in management....