nep-rmg New Economics Papers
on Risk Management
Issue of 2024‒02‒26
23 papers chosen by



  1. Spurious Default Probability Projections in Credit Risk Stress Testing Models By Bernd Engelmann
  2. Cash non-additive risk measures: horizon risk and generalized entropy By Giulia Di Nunno; Emanuela Rosazza Gianni
  3. Cyclical systemic risk and banks’ vulnerability By Alona Shmygel; Steven Ongena
  4. Default correlation impact on the loan portfolio credit risk measurement for the "green" finance as an example By Henry Penikas
  5. The Risk-Return Relation in the Corporate Loan Market By Miguel A. Duran
  6. Cross-Domain Behavioral Credit Modeling: transferability from private to central data By O. Didkovskyi; N. Jean; G. Le Pera; C. Nordio
  7. Forecasting and Backtesting Gradient Allocations of Expected Shortfall By Takaaki Koike; Cathy W. S. Chen; Edward M. H. Lin
  8. How would the war and the pandemic affect the stock and cryptocurrency cross-market linkages? By Georgios Bampinas; Theodore Panagiotidis
  9. Navigating extreme market fluctuations: asset allocation strategies in developed vs. emerging economies. By Bonga-Bonga, Lumengo; Montshioa, Keitumetse
  10. Forecasting Volatility of Oil-based Commodities: The Model of Dynamic Persistence By Jozef Barunik; Lukas Vacha
  11. Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review By Lars Ericson; Xuejun Zhu; Xusi Han; Rao Fu; Shuang Li; Steve Guo; Ping Hu
  12. Interest Rate Risk at US Credit Unions By Grant Rosenberger; Peter Zimmerman
  13. Elevated Option-Implied Interest Rate Volatility and Downside Risks to Economic Activity By Cisil Sarisoy
  14. Does FinTech Increase Bank Risk Taking? By Mr. Selim A Elekdag; Drilona Emrullahu; Sami Ben Naceur
  15. Forecasting Growth-at-Risk of the United States: Housing Price versus Housing Sentiment or Attention By Oguzhan Cepni; Rangan Gupta; Christian Pierdzioch
  16. The impact of macroeconomic and monetary policy shocks on credit risk in the euro area corporate sector By Lo Duca, Marco; Moccero, Diego; Parlapiano, Fabio
  17. A Novel Decision Ensemble Framework: Customized Attention-BiLSTM and XGBoost for Speculative Stock Price Forecasting By Riaz Ud Din; Salman Ahmed; Saddam Hussain Khan
  18. What lessons does the COVID-19 pandemic teach us about banking liquidity and information share in the CEMAC zone? By Djimoudjiel, Djekonbe; T. Rostand, Dany Dombu; MBATINA NODJI, NDILENGAR
  19. What drives banks’ credit standards? An analysis based on a large bank-firm panel By Faccia, Donata; Hünnekes, Franziska; Köhler-Ulbrich, Petra
  20. Optimal Insurance to Maximize Exponential Utility when Premium is Computed by a Convex Functional By Jingyi Cao; Dongchen Li; Virginia R. Young; Bin Zou
  21. From Numbers to Words: Multi-Modal Bankruptcy Prediction Using the ECL Dataset By Henri Arno; Klaas Mulier; Joke Baeck; Thomas Demeester
  22. A Study on KPJ Healthcare Sdn Bhd in Malaysia Performance and Its Determinants. By AZMI, NURUL NAJWANIE FATIEHAH
  23. Predictability of Exchange Rate Density Forecasts for Emerging Economies in the Short Run By Jaqueline Terra Moura Marins

  1. By: Bernd Engelmann
    Abstract: Credit risk stress testing has become an important risk management device which is used both by banks internally and by regulators. Stress testing is complex because it essentially means projecting a bank's full balance sheet conditional on a macroeconomic scenario over multiple years. Part of the complexity stems from using a wide range of model parameters for, e.g., rating transition, write-off rules, prepayment, or origination of new loans. A typical parameterization of a credit risk stress test model specifies parameters linked to an average economic, the through-the-cycle, state. These parameters are transformed to a stressed state by utilizing a macroeconomic model. It will be shown that the model parameterization implies a unique through-the-cycle portfolio which is unrelated to a bank's current portfolio. Independent of the stress imposed to the model, the current portfolio will have a tendency to propagate towards the through-the-cycle portfolio. This could create unwanted spurious effects on projected portfolio default rates especially when a stress test model's parameterization is inconsistent with a bank's current portfolio.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.08892&r=rmg
  2. By: Giulia Di Nunno; Emanuela Rosazza Gianni
    Abstract: Horizon risk (see arXiv:2301.04971) is studied in the context of cash non-additive fully-dynamic risk measures induced by BSDEs. Furthermore, we introduce a risk measure based on generalized Tsallis entropy which can dynamically evaluate the riskiness of losses considering both horizon risk and interest rate uncertainty. The new q-entropic risk measure on losses can be used as a quantification of capital requirement.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.14443&r=rmg
  3. By: Alona Shmygel (National Bank of Ukraine); Steven Ongena (University of Zurich - Department of Banking and Finance; Swiss Finance Institute; KU Leuven; NTNU Business School; Centre for Economic Policy Research (CEPR))
    Abstract: What is the impact of cyclical systemic risk on future bank profitability? To answer this question, we study a large panel of Ukrainian banks between 2001 and 2023 comprising systemic events and wartime. With linear local projections we study the impact of cyclical systemic risk on bank profitability and following the original Growth-at-Risk approach we utilize quantile local projections to assess its impact on the tails of the future bank-level profitability distribution. We calibrate the countercyclical capital buffer, develop informative “Bank Capital-at-Risk” and “Share of vulnerable banks” indicators, and conduct scenario analyses and stress tests on profitability and capital adequacy.
    Keywords: systemic risk, linear projections, quantile regressions, bank capital, macroprudential policy
    JEL: E58 G21 G32
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:chf:rpseri:rp2409&r=rmg
  4. By: Henry Penikas (Bank of Russia, Russian Federation)
    Abstract: Default correlation parameter has a material impact on the loan portfolio credit risk. Moreover, the impact is more complex than that of the default probability itself. Current study shows that the rise in default correlation can simultaneously lead to multi-directional changes in different types of risk-measures or focus on a single risk measure, but at different confidence levels. The cause for such dual impact lies in the often neglected rising impact of the default rate (DR) distribution bimodality. In general, we evidence that rise in default correlation produces a multiplicative effect of the probability of default (PD): risk measure declines for low PDs and rises for high PDs, but changes are non-proportionate for the same changes in default correlation. Similar effects, in particular, may arise when augmenting the proportion of "green" lending. Moreover, when such a trend is associated with the decline in PD for the "green" sector and PD rise for the "brown" one, there is an overall reduction in the loan portfolio credit risk in the long-run. However, it is witnessed only after its rise in the mid-term. The paper is accompanied with the relevant codes. They enables the interested parties to replicate the findings, as well as to derive credit risk parameters for any given DR time series and model a DR distribution for any set of distribution mixture parameters.
    Keywords: default correlation, bimodal distribution, default rate; cliff effect, mixture of distribution
    JEL: C34 C67 E52 H23 O44
    Date: 2023–12
    URL: http://d.repec.org/n?u=RePEc:bkr:wpaper:wps121&r=rmg
  5. By: Miguel A. Duran
    Abstract: This paper analyzes the hypothesis that returns play a risk-compensating role in the market for corporate revolving lines of credit. Specifically, we test whether borrower risk and the expected return on these debt instruments are positively related. Our main findings support this prediction, in contrast to the only previous work that examined this problem two decades ago. Nevertheless, we find evidence of mispricing regarding the risk of deteriorating firms using their facilities more intensively and during the subprime crisis.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.12315&r=rmg
  6. By: O. Didkovskyi; N. Jean; G. Le Pera; C. Nordio
    Abstract: This paper introduces a credit risk rating model for credit risk assessment in quantitative finance, aiming to categorize borrowers based on their behavioral data. The model is trained on data from Experian, a widely recognized credit bureau, to effectively identify instances of loan defaults among bank customers. Employing state-of-the-art statistical and machine learning techniques ensures the model's predictive accuracy. Furthermore, we assess the model's transferability by testing it on behavioral data from the Bank of Italy, demonstrating its potential applicability across diverse datasets during prediction. This study highlights the benefits of incorporating external behavioral data to improve credit risk assessment in financial institutions.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.09778&r=rmg
  7. By: Takaaki Koike; Cathy W. S. Chen; Edward M. H. Lin
    Abstract: Capital allocation is a procedure for quantifying the contribution of each source of risk to aggregated risk. The gradient allocation rule, also known as the Euler principle, is a prevalent rule of capital allocation under which the allocated capital captures the diversification benefit of the marginal risk as a component of overall risk. This research concentrates on Expected Shortfall (ES) as a regulatory standard and focuses on the gradient allocations of ES, also called ES contributions. We achieve the comprehensive treatment of backtesting the tuple of ES contributions in the framework of the traditional and comparative backtests based on the concepts of joint identifiability and multi-objective elicitability. For robust forecast evaluation against the choice of scoring function, we further develop Murphy diagrams for ES contributions as graphical tools to check whether one forecast dominates another under a class of scoring functions. Finally, leveraging the recent concept of multi-objective elicitability, we propose a novel semiparametric model for forecasting dynamic ES contributions based on a compositional regression model. In an empirical analysis of stock returns we evaluate and compare a variety of models for forecasting dynamic ES contributions and demonstrate the outstanding performance of the proposed model.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.11701&r=rmg
  8. By: Georgios Bampinas (Department of Economics and Regional Development, Panteion University of Social and Political Sciences, Greece); Theodore Panagiotidis (Department of Economics, University of Macedonia, Greece)
    Abstract: This paper studies the cross-market linkages between six international stock markets and the two major cryptocurrency markets during the Covid-19 pandemic and the Russian invasion of Ukraine. By employing the local (partial) Gaussian correlation approach, we find that during the Covid-19 pandemic period, both cryptocurrency markets possess limited diversification and safe haven properties, which further diminish during the war. Bootstrap tests for contagion suggest that during the Covid-19 pandemic, the East Asian markets lead the transmission of contagion towards the two cryptocurrency markets. During the Russian invasion, the US stock market emerges as the principal transmitter of contagion. Uncovering the role of pandemic (Infectious Disease EMV Index) and geopolitical risk (GPR index) induced uncertainties, we find that under conditions of high uncertainty and falling prices, the dependency between the US and UK stock markets with both cryptocurrency markets increases considerably. The latter is more profound during the Russian-Ukrainian conflict. Our findings are useful for investors in their search for understanding the differences in asymmetric connectedness between markets during extreme events.
    Keywords: Bitcoin, Ethereum, cryptocurrency, stock market, tail dependence, local Gaussian partial correlation, pandemic uncertainty, geopolitical risk uncertainty
    JEL: F31 F37 O16 Q40 G11 G12
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:rim:rimwps:24-01&r=rmg
  9. By: Bonga-Bonga, Lumengo; Montshioa, Keitumetse
    Abstract: This paper contributes to the literature on portfolio allocation by assessing how assets from emerging and developed stock markets can be allocated efficiently during crisis periods. Towards this end, the paper proposes an approach to portfolio allocation that combines traditional portfolio theory with extreme value theory (EVT) based on Generalised Pareto Distributions (GPDs) and Generalised Extreme Values (GEVs). The results of the empirical analysis show that for the mean-variance portfolio constructed from GPD, the emerging market portfolio outperforms both the international portfolio, the combination of emerging and developed market assets, and the developed market portfolio. However, the developed market portfolio outperforms the emerging market portfolio for the mean-variance portfolio constructed from GEV distribution. The paper attributes these different outcomes to the intended objectives of these extreme-value approaches in the context of portfolio selection. These results offer essential guidance for investors and asset managers during the construction of portfolios in times of crisis. They highlight that the effectiveness of a portfolio is significantly influenced by its predefined objectives. Ultimately, these objectives are crucial in deciding the most suitable approach for portfolio construction.
    Keywords: Extreme Value Theory; General Pareto Distribution; Emerging and developed markets; portfolio optimisation; mean-variance.
    JEL: C58 G11 G15
    Date: 2024–01–17
    URL: http://d.repec.org/n?u=RePEc:pra:mprapa:119910&r=rmg
  10. By: Jozef Barunik; Lukas Vacha
    Abstract: Time variation and persistence are crucial properties of volatility that are often studied separately in oil-based volatility forecasting models. Here, we propose a novel approach that allows shocks with heterogeneous persistence to vary smoothly over time, and thus model the two together. We argue that this is important because such dynamics arise naturally from the dynamic nature of shocks in oil-based commodities. We identify such dynamics from the data using localised regressions and build a model that significantly improves volatility forecasts. Such forecasting models, based on a rich persistence structure that varies smoothly over time, outperform state-of-the-art benchmark models and are particularly useful for forecasting over longer horizons.
    Date: 2024–02
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2402.01354&r=rmg
  11. By: Lars Ericson; Xuejun Zhu; Xusi Han; Rao Fu; Shuang Li; Steve Guo; Ping Hu
    Abstract: In the financial services industry, forecasting the risk factor distribution conditional on the history and the current market environment is the key to market risk modeling in general and value at risk (VaR) model in particular. As one of the most widely adopted VaR models in commercial banks, Historical simulation (HS) uses the empirical distribution of daily returns in a historical window as the forecast distribution of risk factor returns in the next day. The objectives for financial time series generation are to generate synthetic data paths with good variety, and similar distribution and dynamics to the original historical data. In this paper, we apply multiple existing deep generative methods (e.g., CGAN, CWGAN, Diffusion, and Signature WGAN) for conditional time series generation, and propose and test two new methods for conditional multi-step time series generation, namely Encoder-Decoder CGAN and Conditional TimeVAE. Furthermore, we introduce a comprehensive framework with a set of KPIs to measure the quality of the generated time series for financial modeling. The KPIs cover distribution distance, autocorrelation and backtesting. All models (HS, parametric and neural networks) are tested on both historical USD yield curve data and additional data simulated from GARCH and CIR processes. The study shows that top performing models are HS, GARCH and CWGAN models. Future research directions in this area are also discussed.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.10370&r=rmg
  12. By: Grant Rosenberger; Peter Zimmerman
    Abstract: Rising interest rates have prompted concerns about losses on bank assets, especially following the failure of Silicon Valley Bank (SVB) in March 2023. In this working paper, we examine whether US credit unions could be subject to similar losses as banks and analyze how their regulatory capital would be affected. We estimate that after realizing losses from assets that have decreased in value and not yet been sold the overall net worth of the credit union industry would have fallen by 40 percent in 2023:Q1. Unrealized losses were most severe at the largest credit unions. Nonetheless, the bulk of deposits at credit unions were insured, suggesting limited risk of an SVB-style run. In addition, credit union deposit rates are relatively insensitive to market interest rates, providing credit unions with a hedge against a rising rate environment. Overall, credit unions’ balance sheet positions seemed to be more resilient to unrealized interest rate risk than banks’.
    Keywords: credit unions; deposit franchise; interest rate risk
    JEL: G21 G28
    Date: 2024–02–05
    URL: http://d.repec.org/n?u=RePEc:fip:fedcwq:97721&r=rmg
  13. By: Cisil Sarisoy
    Abstract: Measures of uncertainty about U.S. short maturity interest rates derived from options have risen sharply since October 2021, reaching their highest levels in more than a decade. This note first uses survey-based measures of economic uncertainty to argue that this increase in option-implied measures likely reflect higher uncertainty about inflation, the associated monetary policy response, and the perceived resulting downside risks to economic activity.
    Date: 2023–12–22
    URL: http://d.repec.org/n?u=RePEc:fip:fedgfn:2023-12-22&r=rmg
  14. By: Mr. Selim A Elekdag; Drilona Emrullahu; Sami Ben Naceur
    Abstract: Motivated by its rapid growth, this paper investigates how FinTech activities influence risk taking by financial intermediaries (FIs). In this context, this paper revisits an ongoing debate on the impact of competition on financial stability: on one side, it is argued that greater competition encourages greater risk taking (competition-fragility hypothesis), while the other side of the debate asserts that more competition can increase financial stability (competition-stability hypothesis). Using a curated databased covering over 10, 000 FIs and global FinTech activities, we find a robust relationship whereby greater FinTech presence is associated with heightened risk taking by FIs, offering support for the competition-fragility hypothesis. However, the inclusion of bank-, industry-, and country-specific characteristics can alter this relationship. Importantly, there is suggestive evidence indicating that in certain cases, greater FinTech presence may be associated with less FI risk taking amid stronger domestic institutions. Notwithstanding the relevance for policy, this paper presents a novel framework that may help reconcile some of the conflicting results in the literature which have found supportive evidence for each of the two competing hypotheses.
    Keywords: fintech; bank risk taking; competition
    Date: 2024–01–26
    URL: http://d.repec.org/n?u=RePEc:imf:imfwpa:2024/017&r=rmg
  15. By: Oguzhan Cepni (Copenhagen Business School, Department of Economics, Porcelaenshaven 16A, Frederiksberg DK-2000, Denmark; Ostim Technical University, Ankara, Turkiye); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany)
    Abstract: We examine the predictive power of national housing market-related behavioral variables, along with their connectedness at the state level, in forecasting US aggregate economic activity (such as the Chicago Fed National Activity Index (CFNAI) and real Gross Domestic Product (GDP) growth), as opposed to solely relying on state-level housing price return connectedness. Our results reveal that while standard linear regression models show statistically insignificant differences in forecast accuracy between the connectedness of housing price returns and behavioral variables, quantile regression models, which capture growth-at-risk, demonstrate significant forecasting improvements. Specifically, state-level connectedness of housing sentiment enhances forecast accuracy at lower quantiles of economic activity, indicative of downturns, whereas connectedness of housing attention is more effective at upper quantiles, corresponding to upturns. The results for GDP growth, however, are less conclusive. These findings underscore the importance of incorporating regional heterogeneity and behavioral aspects in economic forecasting.
    Keywords: Housing price, Housing sentiment and attention, Connectedness, Economic activity, Forecasting, Quantile predictive regressions
    JEL: C22 C32 C53 E30 R31
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:pre:wpaper:202401&r=rmg
  16. By: Lo Duca, Marco; Moccero, Diego; Parlapiano, Fabio
    Abstract: We analyse the impact of macroeconomic and monetary policy shocks on corporate credit risk as measured by firms’ probabilities of default (PDs) for the four largest euro area countries. We estimate the impact of shocks on one-year PDs using local projections (LP). For the period 2014-19, we find that aggregate shocks significantly affect the dynamics of credit risk. An adverse supply shock leads to a deterioration of firms’ riskiness 10 per cent above the average PD. Contractionary monetary policy shocks exert similar, but delayed effects. Firms’ responses to shocks vary depending on their characteristics and degree of financial constraints. Smaller firms are affected to a larger degree. Firms’ outstanding indebtedness and debt repayment capacity are an important transmission channel for aggregate shocks, but the accumulation of cash reserves helps building resilience. JEL Classification: C23, C55, E43, E52, G33
    Keywords: corporate credit risk, local projections, monetary policy shocks, probabilities of default, structural demand and supply shocks
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:ecb:ecbwps:20242897&r=rmg
  17. By: Riaz Ud Din; Salman Ahmed; Saddam Hussain Khan
    Abstract: Forecasting speculative stock prices is essential for effective investment risk management that drives the need for the development of innovative algorithms. However, the speculative nature, volatility, and complex sequential dependencies within financial markets present inherent challenges which necessitate advanced techniques. This paper proposes a novel framework, CAB-XDE (customized attention BiLSTM-XGB decision ensemble), for predicting the daily closing price of speculative stock Bitcoin-USD (BTC-USD). CAB-XDE framework integrates a customized bi-directional long short-term memory (BiLSTM) with the attention mechanism and the XGBoost algorithm. The customized BiLSTM leverages its learning capabilities to capture the complex sequential dependencies and speculative market trends. Additionally, the new attention mechanism dynamically assigns weights to influential features, thereby enhancing interpretability, and optimizing effective cost measures and volatility forecasting. Moreover, XGBoost handles nonlinear relationships and contributes to the proposed CAB-XDE framework robustness. Additionally, the weight determination theory-error reciprocal method further refines predictions. This refinement is achieved by iteratively adjusting model weights. It is based on discrepancies between theoretical expectations and actual errors in individual customized attention BiLSTM and XGBoost models to enhance performance. Finally, the predictions from both XGBoost and customized attention BiLSTM models are concatenated to achieve diverse prediction space and are provided to the ensemble classifier to enhance the generalization capabilities of CAB-XDE. The proposed CAB-XDE framework is empirically validated on volatile Bitcoin market, sourced from Yahoo Finance and outperforms state-of-the-art models with a MAPE of 0.0037, MAE of 84.40, and RMSE of 106.14.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.11621&r=rmg
  18. By: Djimoudjiel, Djekonbe; T. Rostand, Dany Dombu; MBATINA NODJI, NDILENGAR
    Abstract: The objective of this study is to assess the effect of COVID-19 on the situation of excess liquidity in the CEMAC zone. The results are obtained using Bayesian estimates of VAR models on monthly data on banks ranging from 2000 to 2020 for countries in CEMAC. The main results suggest the shock generated by the COVID-19 pandemic on the economy of the sub-region has contributed to bogging down the situation of excess liquidity. Indeed, on the one hand, the shock on bank liquidity is greater in the short than in the long term. On the other hand, the situation under COVID-19 led to an increase in credit in the first 6 to 8 months of 2020 followed by a drop in the level of risk hedging capital. The health policies adopted and the ensuing recession, on the other hand, significantly affected the level of bank deposits. The main recommendations consist of reducing the climate of information asymmetry by encouraging the implementation of credit registers and establishing policies to help borrowers.
    Keywords: Excess liquidity; Information sharing ; COVID-19; BVAR; CEMAC.
    JEL: C23 D82 E50 O55
    Date: 2024–01–05
    URL: http://d.repec.org/n?u=RePEc:pra:mprapa:119666&r=rmg
  19. By: Faccia, Donata; Hünnekes, Franziska; Köhler-Ulbrich, Petra
    Abstract: In this paper we build a unique dataset to study how banks decide which firms to lend to and how this decision depends on their own situation and the characteristics of their borrowers. We find that weaker capitalised banks adjust their credit standards more than healthier banks, especially for firms with a higher default risk. We also show how credit standards change in reaction to two specific macroeconomic developments, namely an increase in bank funding costs and a sudden deterioration in banks’ corporate loan portfolios. Here we find that weaker banks respond more forcefully by tightening their credit standards more than better capitalised banks. This development is particularly pronounced when banks are linked to riskier firms. Insofar, we provide evidence of heterogeneity in the bank lending channel, depending on the situation of the lenders and the borrowers. JEL Classification: E44, E51, E52, G21
    Keywords: bank lending channel, credit risk, credit supply, monetary policy transmission
    Date: 2024–02
    URL: http://d.repec.org/n?u=RePEc:ecb:ecbwps:20242902&r=rmg
  20. By: Jingyi Cao; Dongchen Li; Virginia R. Young; Bin Zou
    Abstract: We find the optimal indemnity to maximize the expected utility of terminal wealth of a buyer of insurance whose preferences are modeled by an exponential utility. The insurance premium is computed by a convex functional. We obtain a necessary condition for the optimal indemnity; then, because the candidate optimal indemnity is given implicitly, we use that necessary condition to develop a numerical algorithm to compute it. We prove that the numerical algorithm converges to a unique indemnity that, indeed, equals the optimal policy. We also illustrate our results with numerical examples.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.08094&r=rmg
  21. By: Henri Arno; Klaas Mulier; Joke Baeck; Thomas Demeester
    Abstract: In this paper, we present ECL, a novel multi-modal dataset containing the textual and numerical data from corporate 10K filings and associated binary bankruptcy labels. Furthermore, we develop and critically evaluate several classical and neural bankruptcy prediction models using this dataset. Our findings suggest that the information contained in each data modality is complementary for bankruptcy prediction. We also see that the binary bankruptcy prediction target does not enable our models to distinguish next year bankruptcy from an unhealthy financial situation resulting in bankruptcy in later years. Finally, we explore the use of LLMs in the context of our task. We show how GPT-based models can be used to extract meaningful summaries from the textual data but zero-shot bankruptcy prediction results are poor. All resources required to access and update the dataset or replicate our experiments are available on github.com/henriarnoUG/ECL.
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:arx:papers:2401.12652&r=rmg
  22. By: AZMI, NURUL NAJWANIE FATIEHAH
    Abstract: This research looks at the aspects that can impact the outcomes of KPJ Healthcare Sdn Bhd. The goal is to discover internal and external variables, as well as the combination of factors that may have an impact of the performance of KPJ Healthcare Sdn Bhd. To determine the degree of significance of the connection between these variables, methods such as statistical and regression techniques have opted in this research case. When certain variables are considered, it becomes evident that operational risk instead of other determinants has the most significant influence on KPJ Healthcare Sdn Bhd performance. However, despite the fact that the KPJ Healthcare Sdn Bhd controversy in 2022 possibly reveals that the corporation’s poor operational risk management might directly impact their performance as well.
    Keywords: KPJ Healthcare Sdn Bhd, profitability, performance, ROE, corporate governance
    JEL: G3
    Date: 2023–12–30
    URL: http://d.repec.org/n?u=RePEc:pra:mprapa:119810&r=rmg
  23. By: Jaqueline Terra Moura Marins
    Abstract: FX rate predictability is non-trivial, but is of great importance for economic agents and policy makers, as it is one of the main prices in an economy. Aware of the failure of standard economic theory to explain foreign exchange rate behavior using key economic variables since Meese and Rogoff (1983 a, b), in this paper, besides economic models, we also use financial data to forecast point and density estimates, as well as some value-at-risk measures. Making use of promising results found for Brazilian currency in Gaglianone and Marins (2017) with the Option-Implied model for the short-run forecasting, we verify if
    Date: 2024–01
    URL: http://d.repec.org/n?u=RePEc:bcb:wpaper:588&r=rmg

General information on the NEP project can be found at https://nep.repec.org. For comments please write to the director of NEP, Marco Novarese at <director@nep.repec.org>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.