|
on Risk Management |
| By: | Mahmood Alaghmandan; Olga Streltchenko |
| Abstract: | In this paper, we discuss aspects of model risk management in financial institutions which could be adopted by academic institutions to improve the process of conducting academic research, identify and mitigate existing limitations, decrease the possibility of erroneous results, and prevent fraudulent activities. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.14776 |
| By: | Liyang Wang; Yu Cheng; Ao Xiang; Jingyu Zhang; Haowei Yang |
| Abstract: | This paper explores the application of Natural Language Processing (NLP) in financial risk detection. By constructing an NLP-based financial risk detection model, this study aims to identify and predict potential risks in financial documents and communications. First, the fundamental concepts of NLP and its theoretical foundation, including text mining methods, NLP model design principles, and machine learning algorithms, are introduced. Second, the process of text data preprocessing and feature extraction is described. Finally, the effectiveness and predictive performance of the model are validated through empirical research. The results show that the NLP-based financial risk detection model performs excellently in risk identification and prediction, providing effective risk management tools for financial institutions. This study offers valuable references for the field of financial risk management, utilizing advanced NLP techniques to improve the accuracy and efficiency of financial risk detection. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.09765 |
| By: | Nguyen, Quang Khai |
| Abstract: | In the context of emerging countries trying to attract foreign investors, building governance strategies and risk management of firms is an increasing concern. This study investigates the impact of financial flexibility strategies on the risk management effectiveness of firms and mechanism of these impacts by focusing on Vietnamese listed firms by applying the fixed effect and system GMM methods on a sample of 635 Vietnamese listed firms during the 2010–2021 period to derive empirical models under the high risk-high return approach. We also applied robustness tests to ensure that the results are reliable. We also investigate the level of risk management effectiveness among these firms during the 2010–2021 period. We found that financial flexibility strategies negatively impact risk management effectiveness of firms through reducing both firm risk and firm performance. Furthermore, we found that the degree of risk management effectiveness differs between low- and high-risk firms in Vietnam, with low-risk firms displaying more effective risk management compared to high-risk firms. Our research shows that financial flexibility strategies are not conducive to risk management effectiveness; however, firms can control the impact of flexibility strategies on risk management by controlling firm performance and risk. |
| Keywords: | financial flexibility, risk management effectiveness, listed firm, Vietnam |
| JEL: | G13 G18 G3 |
| Date: | 2024–05–01 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:121162 |
| By: | Natalia Roszyk (University of Warsaw, Faculty of Economic Sciences, Quantitative Finance Research Group); Robert Ślepaczuk (University of Warsaw, Faculty of Economic Sciences, Quantitative Finance Research Group, Department of Quantitative Finance and Machine Learning) |
| Abstract: | Predicting the S&P 500 index's volatility is crucial for investors and financial analysts as it helps in assessing market risk and making informed investment decisions. Volatility represents the level of uncertainty or risk related to the size of changes in a security's value, making it an essential indicator for financial planning. This study explores four methods to improve the accuracy of volatility forecasts for the S&P 500: the established GARCH model, known for capturing historical volatility patterns; an LSTM network that utilizes past volatility and log returns; a hybrid LSTM-GARCH model that combines the strengths of both approaches; and an advanced version of the hybrid model that also factors in the VIX index to gauge market sentiment. This analysis is based on a daily dataset that includes data for S&P 500 and VIX index, covering the period from January 3, 2000, to December 21, 2023. Through rigorous testing and comparison, we found that machine learning approaches, particularly the hybrid LSTM models, significantly outperform the traditional GARCH model. The inclusion of the VIX index in the hybrid model further enhances its forecasting ability by incorporating real-time market sentiment. The results of this study offer valuable insights for achieving more accurate volatility predictions, enabling better risk management and strategic investment decisions in the volatile environment of the S&P 500. |
| Keywords: | volatility forecasting, LSTM-GARCH, S&P 500 index, hybrid forecasting models, VIX index, machine learning, financial time series analysis, walk-forward process, hyperparameters tuning, deep learning, recurrent neural networks |
| JEL: | C4 C45 C55 C65 G11 |
| Date: | 2024 |
| URL: | https://d.repec.org/n?u=RePEc:war:wpaper:2024-13 |
| By: | Mihaela Nistor |
| Abstract: | Keynote Remarks at the XLoD Global – New York Conference, New York City. |
| Keywords: | risk management; artificial intelligence (AI) |
| Date: | 2024–06–11 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fednsp:98431 |
| By: | Fernando Acebes; Javier Pajares; Jose M Gonzalez-Varona; Adolfo Lopez-Paredes |
| Abstract: | Project managers need to manage risks throughout the project lifecycle and, thus, need to know how changes in activity durations influence project duration and risk. We propose a new indicator (the Activity Risk Index, ARI) that measures the contribution of each activity to the total project risk while it is underway. In particular, the indicator informs us about what activities contribute the most to the project's uncertainty so that project managers can pay closer attention to the performance of these activities. The main difference between our indicator and other activity sensitivity metrics in the literature (e.g. cruciality, criticality, significance, or schedule sensitivity indices) is that our indicator is based on the Schedule Risk Baseline concept instead of on cost or schedule baselines. The new metric not only provides information at the beginning of the project, but also while it is underway. Furthermore, the ARI is the only one to offer a normalized result: if we add its value for each activity, the total sum is 100%. |
| Date: | 2024–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.00078 |
| By: | Viral V. Acharya; Nicola Cetorelli; Bruce Tuckman |
| Abstract: | Nonbank financial institutions (NBFIs) are growing, but banks support that growth via funding and liquidity insurance. The transformation of activities and risks from banks to a bank-NBFI nexus may have benefits in normal states of the world, as it may result in overall growth in (especially, credit) markets and widen access to a wide range of financial services, but the system may be disproportionately exposed to financial and economic instability when aggregate tail risk materializes. In this post, we consider the systemic implications of the observed build-up of bank-NBFI connections associated with the growth of NBFIs. |
| Keywords: | nonbank financial institutions (NBFIs); non-bank financial intermediaries; nonbanks; systemic risk; spillovers; bank regulation |
| JEL: | G01 G21 G23 G28 |
| Date: | 2024–06–20 |
| URL: | https://d.repec.org/n?u=RePEc:fip:fednls:98461 |
| By: | Lukas Gonon; Antoine Jacquier; Ruben Wiedemann |
| Abstract: | We devise a novel method for implied volatility smoothing based on neural operators. The goal of implied volatility smoothing is to construct a smooth surface that links the collection of prices observed at a specific instant on a given option market. Such price data arises highly dynamically in ever-changing spatial configurations, which poses a major limitation to foundational machine learning approaches using classical neural networks. While large models in language and image processing deliver breakthrough results on vast corpora of raw data, in financial engineering the generalization from big historical datasets has been hindered by the need for considerable data pre-processing. In particular, implied volatility smoothing has remained an instance-by-instance, hands-on process both for neural network-based and traditional parametric strategies. Our general operator deep smoothing approach, instead, directly maps observed data to smoothed surfaces. We adapt the graph neural operator architecture to do so with high accuracy on ten years of raw intraday S&P 500 options data, using a single set of weights. The trained operator adheres to critical no-arbitrage constraints and is robust with respect to subsampling of inputs (occurring in practice in the context of outlier removal). We provide extensive historical benchmarks and showcase the generalization capability of our approach in a comparison with SVI, an industry standard parametrization for implied volatility. The operator deep smoothing approach thus opens up the use of neural networks on large historical datasets in financial engineering. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.11520 |
| By: | Siema Hashemi (CEMFI, Centro de Estudios Monetarios y Financieros) |
| Abstract: | This paper investigates the impact of supervisory resolution tools, specifically bail-ins versus bailouts, on the ex-ante banks’ portfolio composition and resulting ex-post default probabilities in the presence of both idiosyncratic and systematic shocks. Banks make decisions regarding short-term versus long-term risky investments while considering the expected resolution policy. I find that both types of shocks can generate financial instability, which the two resolution tools address through distinct channels. With only idiosyncratic shocks, creditor bailouts, acting as debt insurance, eliminate the equilibrium with bank defaults, while bail-ins induce banks to invest less in the risky short-term asset, which may also prevent defaults. In the presence of both shocks, creditor bailouts can prevent systemic defaults, while bail-ins are less effective in preventing them and could even contribute to systemic risk. |
| Keywords: | Bailouts, bail-ins, bank resolution, systemic risk, bank portfolio allocation, fire sales. |
| JEL: | G21 G28 G33 |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:cmf:wpaper:wp2024_2410 |
| By: | Behn, Markus; Cornacchia, Wanda; Forletta, Marco; Jarmulska, Barbara; Perales, Cristian; Ryan, Ellen; Serra, Diogo; Tereanu, Eugen; Tumino, Marcello; Abreu, Daniel; Ciampi, Francesco; Ciocchetta, Federica; Drenkovska, Marija; Fritz, Benedikt; Geiger, Sebastian; Melnychuk, Mariya; Meusel, Steffen; Reginster, Alexandre; Rychtárik, Štefan; Vilka, Ilze; Virel, Fleurilys |
| Abstract: | The 2019 revision to the Capital Requirements Directive allowed the systemic risk buffer to be applied on a sectoral basis in the European Union. Since then an increasing number of countries have implemented the new tool, primarily to address vulnerabilities in the residential real estate sector. To inform and foster a consistent understanding and application of the buffer, this paper proposes two specific methodologies. First, an indicator-based approach which provides an aggregate measure of cyclical vulnerabilities in the residential real estate sector and can signal a potential need to activate a sectoral buffer to address them. Second, a model-based approach following a stress test rationale simulating mortgage loan losses under adverse conditions, which can be used as a starting point for calibrating a sectoral buffer. Besides these methodological contributions, the paper conceptually discusses the interaction between the sectoral buffer and other prudential requirements and instruments, ex ante and ex post policy impact assessment, and factors guiding the possible release of the buffer. Finally, the paper considers possible future applications of sectoral buffer requirements for other types of sectoral vulnerabilities, for example in relation to commercial real estate, exposures to non-financial corporations or climate-related risks. JEL Classification: G21, G28 |
| Keywords: | banks, capital buffers, financial stability, macroprudential policy |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbops:2024352 |
| By: | Nie, George Y. (Concordia University) |
| Abstract: | Nie (2023) argues that asset risk is cumulative over the holding time length, suggesting that the literature misses the indispensable dimension of time length of managerial risk bound with asset untradability. Using a dummy orthogonalization methodology, I illustrate that the inside debt reduces the effect of age (which negatively proxies maturity) on managerial risk-shifting incentives in M&As, implying that the inside debt risk (captured as risk premium over maturity) approaches zero as maturity approaches zero. An experiment and instrumental variable approach confirm the evidence. The results complement Nie (2023) and challenge, thereby fixing, agency theories such as Jensen and Meckling (1976). |
| Date: | 2024–06–28 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:jd3c2 |
| By: | Schick, Manuel |
| Abstract: | This paper investigates nowcasting Growth-at-Risk (GaR) using consensus forecasts from the Survey of Professional Forecasters (SPF) in the US. Incorporating SPF consensus forecasts into the conditional mean of an AR-GARCH type model significantly enhances nowcasting accuracy for GaR and the conditional density of GDP growth. While there is strong time variation in both the lower and upper quantiles of the GDP growth distribution, integrating skewness and fat tails into the model does not improve forecasting accuracy. By accounting for changes in the conditional mean of the GDP growth distribution over time, these findings highlight the value of SPF consensus projections for GaR nowcasting. |
| Keywords: | Growth-at-Risk; GARCH; Survey of Professional Forecasters |
| Date: | 2024–06–25 |
| URL: | https://d.repec.org/n?u=RePEc:awi:wpaper:0750 |
| By: | Chen Tong; Peter Reinhard Hansen; Ilya Archakov |
| Abstract: | We introduce a novel multivariate GARCH model with flexible convolution-t distributions that is applicable in high-dimensional systems. The model is called Cluster GARCH because it can accommodate cluster structures in the conditional correlation matrix and in the tail dependencies. The expressions for the log-likelihood function and its derivatives are tractable, and the latter facilitate a score-drive model for the dynamic correlation structure. We apply the Cluster GARCH model to daily returns for 100 assets and find it outperforms existing models, both in-sample and out-of-sample. Moreover, the convolution-t distribution provides a better empirical performance than the conventional multivariate t-distribution. |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2406.06860 |
| By: | Kejin Wu (Department of Mathematics, University of California San Diego); Sayar Karmakar (Department of Statistics, University of Florida); Rangan Gupta (Department of Economics, University of Pretoria) |
| Abstract: | In this work, we explore the forecasting ability of a recently proposed normalizing and variance-stabilizing (NoVaS) transformation with the possible inclusion of exogenous variables. From an applied point-of-view, extra knowledge such as fundamentals- and sentiments-based information could be beneficial to improve the prediction accuracy of market volatility if they are incorporated into the forecasting process. In the classical approach, these models including exogenous variables are typically termed GARCHX-type models. Being a Model-free prediction method, NoVaS has generally shown more accurate, stable and robust (to misspecifications) performance than that compared to classical GARCH-type methods. This motivates us to extend this framework to the GARCHX forecasting as well. We derive the NoVaS transformation needed to include exogenous covariates and then construct the corresponding prediction procedure. We show through extensive simulation studies that bolster our claim that the NoVaS method outperforms traditional ones, especially for long-term time aggregated predictions. We also provide an interesting data analysis to exhibit how our method could possibly shed light on the role of geopolitical risks in forecasting volatility in national stock market indices for three different countries in Europe. |
| Keywords: | Volatility forecasting, Model-free prediction, GARCH, GARCHX |
| JEL: | C32 C53 C63 Q54 |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:pre:wpaper:202425 |
| By: | Benjamin J. Keys; Philip Mulder |
| Abstract: | We develop a new dataset to study homeowners insurance. Our data on over 47 million observations of households’ property insurance expenditures from 2014-2023 are inferred from mortgage escrow payments. First, we find a sharp 33% increase in average premiums from 2020 to 2023 (13% in real terms) that is highly uneven across geographies. This growth is associated with a stronger relationship between premiums and local disaster risk: A one standard-deviation increase in disaster risk is associated with $500 higher premiums in 2023, up from $300 in 2018. Second, using the rapid rise in reinsurance prices as a natural experiment, we show that the increase in the risk-to-premium gradient was largely caused by the pass-through of reinsurance costs. Third, we project that if the reinsurance shock persists, growing disaster risk will lead climate-exposed households to face $700 higher annual premiums by 2053. Our results highlight that prices in global reinsurance markets pass through to household budgets, and will ultimately drive the cost of rising climate risk. |
| JEL: | G21 G22 G52 Q54 R31 |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:32579 |
| By: | Nie, George Y. (Concordia University) |
| Abstract: | This study argues that a future payment’s risk approaches zero as maturity approaches zero. We employ two factors to model the risk-free rate (which is captured by the central bank’s short-term interest rate) that the market expects the current monetary policy to move towards the neutral level over a certain period. Our 3-factor final model thus splits recent US and Canada T-bill yields into the risk and risk-free rate, explaining 97% of the yields, providing a gateway to bond risk. |
| Date: | 2024–06–25 |
| URL: | https://d.repec.org/n?u=RePEc:osf:socarx:2dazg |
| By: | William N. Goetzmann; Dasol Kim; Robert J. Shiller |
| Abstract: | Over the past two decades, respondents to the Shiller Investor Confidence Surveys assess the probability of a catastrophic stock market crash to be much higher that the historical frequency of such events. We decompose these crash probabilities into fundamental and subjective components and use a large language model to estimate the emotional content of respondent narratives. The subjective crash component is strongly associated with high negative affect. We use respondent location to test how news of unusual exogenous shocks affects crash belief formation. The results are consistent the risk-as-feelings hypothesis and suggest a path by which emotional response to news about salient events may play a role in the scale and variation in investor beliefs about rare disasters. |
| JEL: | E03 G00 G02 G11 G23 |
| Date: | 2024–06 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:32589 |
| By: | Whelan, Karl |
| Abstract: | Samuelson (1963) conjectured that accepting multiple independent gambles you would reject on a stand-alone basis violated expected utility theory. Ross (1999) and others presented examples where expected utility maximizers would accept multiple gambles that would be rejected on a stand-alone basis once the number of gambles gets large enough. We show that a stronger result than Samuelson's conjecture applies for DARA preferences over wealth. Expected utility maximizers with DARA preferences have threshold levels of wealth such that those above the threshold will accept N positive expected value gambles while those below will not and these thresholds are increasing with N. |
| Keywords: | Risk aversion; Paul Samuelson; Law of large numbers |
| JEL: | D81 |
| Date: | 2024–07–04 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:121384 |