nep-rmg New Economics Papers
on Risk Management
Issue of 2023‒07‒17
24 papers chosen by
Stan Miles
Thompson Rivers University

  1. Discretionary decisions in capital requirements under Solvency II By Grochola, Nicolaus; Schlütter, Sebastian
  2. Forecasting the Conditional Distribution of Realized Volatility of Oil Price Returns: The Role of Skewness over 1859 to 2023 By Rangan Gupta; Qiang Ji; Christian Pierdzioch; Vasilios Plakandaras
  3. Connectedness and risk spillovers between crude oil and clean energy stock markets By Çevik, Emre; Çevik, Emrah İsmail; Dibooglu, Sel; Cergibozan, Raif; Bugan, Mehmet Fatih; Destek, Mehmet Akif
  4. Insights into credit loss rates: a global database By Li Lian Ong; Min Wei; Christian Schmieder
  5. Combining Reinforcement Learning and Barrier Functions for Adaptive Risk Management in Portfolio Optimization By Zhenglong Li; Hejun Huang; Vincent Tam
  6. Bias-reduced and variance-corrected asymptotic Gaussian inference about extreme expectiles By Daouia, Abdelaati; Stupfler, Gilles; Usseglio-Carleve, Antoine
  7. Categorical Economic Policy Uncertainties and Tail Risk in Energy Markets: A Connectedness Analysis By Etienne, Xiaoli L.; Durongkadej, Isarin; Scarcioffolo, Alexandre
  8. Consumption Partial Insurance in the Presence of Tail Income Risk By Anisha Ghosh; Alexandros Theloudis
  9. Estimation of Large Volatility Matrices with Low-Rank Signal Plus Sparse Noise Structures By Runyu Dai; Yasumasa Matsuda
  10. Life after (Soft) Default By Giacomo De Giorgi; Costanza Naguib
  11. The demand for long-term mortgage contracts and the role of collateral By Liu, Lu
  12. Demand-supply imbalance risk and long-term swap spreads By Hanson, Samuel; Malkhozov, Aytek; Venter, Gyuri
  13. Using Extreme Value Theory to Improve Knowledge and Decision Making of Low Probability Events. By Van Tassell, Gerald H.; Walters, Cory G.; Preston, Richard K.; Mallory, Mindy L.
  14. Optimizing Investment Strategies with Lazy Factor and Probability Weighting: A Price Portfolio Forecasting and Mean-Variance Model with Transaction Costs Approach By Shuo Han; Yinan Chen; Jiacheng Liu
  15. War Discourse and the Cross Section of Expected Stock Returns By David Hirshleifer; Dat Mai; Kuntara Pukthuanthong
  16. Copula-Based Trading of Cointegrated Cryptocurrency Pairs By Masood Tadi; Jiří Witzany
  17. Advantageous selection without moral hazard By Philippe de Donder; Marie-Louise Leroux; François Salanié
  18. Optimal Investment with Stochastic Interest Rates and Ambiguity By Julian H\"olzermann
  19. Competition and Risk Taking in Local Bank Markets: Evidence from the Business Loans Segment By Chiara Canta; Øivind A. Nilsen; Simen A. Ulsaker; Øivind Anti Nilsen
  20. Global Liquidity: Drivers, Volatility and Toolkits By Linda S. Goldberg
  21. Private Firm Repayment Vulnerabilities and Adverse Economic Conditions By Matt Darst; Mary Zhang
  22. A Parsimonious Inverse Cox-Ingersoll-Ross Process for Financial Price Modeling By Li Lin; Didier Sornette
  23. Modeling and evaluating conditional quantile dynamics in VaR forecasts By Fabrizio Cipollini; Giampiero M. Gallo; Alessandro Palandri
  24. Support Vector Machines and Bankruptcy Prediction By Zazueta, Jorge; Zazueta-Hernández, Jorge; Heredia, Andrea Chavez

  1. By: Grochola, Nicolaus; Schlütter, Sebastian
    Abstract: The capital requirements of Solvency II allow insurers to make discretionary choices. Besides extensive possibilities regarding the choice of a risk model (ranging between a regulatory prescribed standard formula to a full self-developed internal model), insurers can make use of transitional measures and adjustments, which can have a substantial impact on their reported solvency level. The aim of this article is to study the effect of these long-term guarantee measures and to identify drivers of the discretionary decisions. For this purpose, we first assess the risk profile of 49 European insurers by estimating the sensitivities of their stock returns to movements in market risk drivers, such as interest rates and credit spreads. In a second step, we analyze to what extent insurers' risk profiles influence their discretionary decisions in the capital requirement calculation. We gather information on discretionary decisions based on hand-collected Solvency II data for the years 2016 to 2020. We find that insurers optimize their reported solvency situation by making discretionary decisions in such a way that capital requirements for material risk drivers are clearly reduced. For instance, we find that the usage of the volatility adjustment is positively related to the interest rate risk as perceived by financial markets, even when controlling for the portion of life insurance in technical provisions. Similarly, the matching adjustment is linked to significantly higher credit risk sensitivities. Our results point out that due to discretionary decisions Solvency II figures can substantially deviate from a market-oriented, risk-based view on insurance companies' risk situation.
    Keywords: Solvency II, capital requirements, discretionary decisions
    Date: 2023
  2. By: Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Qiang Ji (Institutes of Science and Development, Chinese Academy of Sciences, Beijing, China; School of Public Policy and Management, University of Chinese Academy of Sciences, Beijing, China); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany); Vasilios Plakandaras (Department of Economics, Democritus University of Thrace, Komotini, 69100, Greece)
    Abstract: We examine the predictive value of expected skewness of oil returns for the corresponding realized volatility using monthly data for the entire modern history of the oil industry, covering 1859:11 to 2023:04. We utilize a quantile predictive regression model, which is able to accommodate nonlinearity and structural breaks. In-sample results show that the predictive impact of expected skewness on realized volatility can be both positive and negative, with these signs contingent on the quantiles of realized volatility. Moreover, we detected statistically significant forecasting gains that arise at the extreme ends and around the median of the conditional distribution of realized volatility, at 1-, 3-, 6- and, particularly, 12-month-ahead horizons. Our results have important implications for academics, investors and policymakers.
    Keywords: Oil Returns, Expected Skewness, Realized Volatility, Quantile Regression, Forecasting
    JEL: C22 C53 Q02
    Date: 2023–06
  3. By: Çevik, Emre; Çevik, Emrah İsmail; Dibooglu, Sel; Cergibozan, Raif; Bugan, Mehmet Fatih; Destek, Mehmet Akif
    Abstract: This research investigates the relationship between clean energy stock and oil market returns utilizing Granger predictability in distribution and quantile impulse response analysis. We find that clean energy stock returns Granger predict oil price returns during "normal times" based on the distribution's center, but not vice versa. During bullish market episodes, there is bidirectional Granger predictability between the returns of clean energy stocks and oil market returns. Nonetheless, we find that clean energy stock returns Granger predict oil returns in bearish markets without any evidence of the contrary. This indicates that oil returns cannot be used to hedge the downside risk associated with renewable energy company purchases. Quantile impulse responses for the relationship between clean energy stocks and the crude oil market reveal bidirectional and significant responses, where a negative shock during an extremely down market reveals a negative response in the other market and a positive shock during an extremely up market reveals a significant positive response. This shows that neither market can be utilized to offset risks in the other market.
    Keywords: Clean energy returns; oil returns; risk spillovers; the hedging
    JEL: G1
    Date: 2022–09–25
  4. By: Li Lian Ong; Min Wei; Christian Schmieder
    Abstract: Credit risk has played a significant role in many financial crises, including the great financial crisis. The COVID-19 pandemic also highlighted bank credit losses to the private sector. However, there remains a significant gap in terms of reliable economy-level credit risk data for financial stability analysis, given that such information is not readily available to the public in any systematic manner. Building upon the work of Hardy and Schmieder (2020), we derive time series of actual as well as forward-looking market- and macro-implied credit loss rates for the majority of jurisdictions around the world. Our database, intended as a public good, is available through a user-friendly interactive dashboard, which allows downloads of credit loss rate time series for the desired jurisdiction(s). Users are also able to run simple scenario analyses based on their projected GDP paths. The data series will be updated on an ongoing basis as new information is published by the original sources.
    Keywords: credit risk, credit loss rates, data gap, forward-looking, loss given default (LGD), macro-implied, probability of default (PD), stress test
    JEL: F34 E44 E52 G28 G32 P52
    Date: 2023–05
  5. By: Zhenglong Li; Hejun Huang; Vincent Tam
    Abstract: Reinforcement learning (RL) based investment strategies have been widely adopted in portfolio management (PM) in recent years. Nevertheless, most RL-based approaches may often emphasize on pursuing returns while ignoring the risks of the underlying trading strategies that may potentially lead to great losses especially under high market volatility. Therefore, a risk-manageable PM investment framework integrating both RL and barrier functions (BF) is proposed to carefully balance the needs for high returns and acceptable risk exposure in PM applications. Up to our understanding, this work represents the first attempt to combine BF and RL for financial applications. While the involved RL approach may aggressively search for more profitable trading strategies, the BF-based risk controller will continuously monitor the market states to dynamically adjust the investment portfolio as a controllable measure for avoiding potential losses particularly in downtrend markets. Additionally, two adaptive mechanisms are provided to dynamically adjust the impact of risk controllers such that the proposed framework can be flexibly adapted to uptrend and downtrend markets. The empirical results of our proposed framework clearly reveal such advantages against most well-known RL-based approaches on real-world data sets. More importantly, our proposed framework shed lights on many possible directions for future investigation.
    Date: 2023–06
  6. By: Daouia, Abdelaati; Stupfler, Gilles; Usseglio-Carleve, Antoine
    Abstract: The expectile is a prime candidate for being a standard risk measure in actuarial and financial contexts, for its ability to recover information about probabilities and typical behavior of extreme values as well as its excellent axiomatic properties. A series of recent papers has focused on expectile estimation at extreme levels, with a view on gathering essential information about low-probability, high-impact events that are of most interest to risk managers. The obtention of accurate confidence intervals for extreme expectiles is paramount in any decision process in which they are involved, but actual inference on these tail risk measures is still a difficult question due to their least squares nature and sensitivity to tail heaviness. This article focuses on asymptotic Gaussian inference about tail expectiles in the challenging context of heavy-tailed observations. We use an in-depth analysis of the proofs of asymptotic normality results for two classes of extreme expectile estimators to derive bias-reduced and variance-corrected Gaussian confidence intervals. These, unlike previous attempts in the literature, are well-rooted in statistical theory and can accommodate underlying distributions that display a wide range of tail behaviors. A large-scale simulation study and three real data analyses confirm the versatility of the proposed technique.
    Keywords: Asymptotic normality; Bias correction; Expectiles; Extreme values; Heavy tails; Inference; Variance correction
    Date: 2023–06–07
  7. By: Etienne, Xiaoli L.; Durongkadej, Isarin; Scarcioffolo, Alexandre
    Keywords: Risk and Uncertainty, Resource/Energy Economics and Policy, International Development
    Date: 2023
  8. By: Anisha Ghosh; Alexandros Theloudis
    Abstract: We measure the extent of consumption insurance to income shocks accounting for high-order moments of the income distribution. We derive a nonlinear consumption function, in which the extent of insurance varies with the sign and magnitude of income shocks. Using PSID data, we estimate an asymmetric pass-through of bad versus good permanent shocks -- 17% of a 3 sigma negative shock transmits to consumption compared to 9% of an equal-sized positive shock -- and the pass-through increases as the shock worsens. Our results are consistent with surveys of consumption responses to hypothetical events and suggest that tail income risk matters substantially for consumption.
    Date: 2023–06
  9. By: Runyu Dai; Yasumasa Matsuda
    Abstract: In this paper, we propose a parsimonious model to estimate large volatility matrices by combining DCC-GARCH, sparsity-induced weak factors (sWFs) and POET framework in Fan et al. (2013). We call this method the DCC and sWFs extended POET (DCC-ePOET). Built on the mixed factor structures, we estimate volatility matrices through the univariate volatilities of observable factors and weak latent factors with a linear transformation. We further include a sparse noise covariance estimator obtained by an aptivethreshold method proposed in POET to dressthe singularity issue when the cross-sectional dimension N is larger than the sample size T, and capture the weak correlations in the factor models'idiosyncratic terms. Simulation studies show that our proposed method achieves good finite-sample performance. Empirical studies demonstrate that the developed method is superior to several candidates in the analysis of out-of-sample minimum variance portfolio allocations.
    Date: 2023–06
  10. By: Giacomo De Giorgi; Costanza Naguib
    Abstract: We analyze the impact of soft credit default (i.e. a delinquency of 90+ days) on individual trajectories. Using a proprietary dataset on about 2 million individuals for the years 2004 to 2020, we find that a soft default has substantial and long-lasting (i.e. up to ten years after the event) negative effects on credit score, total credit limit, home-ownership status, and income.
    Date: 2023–06
  11. By: Liu, Lu
    Abstract: Long-term fixed-rate mortgage contracts protect households against interest rate risk, yet most countries have relatively short interest rate fixation lengths. Using administrative data from the UK, the paper finds that the choice of fixation length tracks the life-cycle decline of credit risk in the mortgage market: the loan-to-value (LTV) ratio decreases and collateral coverage improves over the life of the loan due to principal repayment and house price apprecia-tion. High-LTV borrowers, who pay large initial credit spreads, trade off their insurance motive against reducing credit spreads over time using shorter-term contracts. To quantify demand for long-term contracts, I develop a life-cycle model of optimal mortgage fixation choice. With baseline house price growth and interest rate risk, households prefer shorter-term contracts at high LTV levels, and longer-term contracts once LTV is sufficiently low, in line with the data. The mechanism helps explain reduced and heterogeneous demand for long-term mortgage contracts. JEL Classification: D15, E43, G21, G22, G5, G52
    Keywords: credit risk, household finance, household risk management, house prices, interest rate risk, mortgage choice
    Date: 2023–07
  12. By: Hanson, Samuel; Malkhozov, Aytek; Venter, Gyuri
    Abstract: We develop a model in which long-term swap spreads are determined by end users' demand for swaps, constrained dealers' supply of swaps, and the risk of future imbalances between demand and supply. Exploiting the sign restrictions implied by our model, we estimate these unobserved demand and supply factors using data on swap spreads and a proxy for dealers' swap arbitrage positions. We find that demand and supply play equally important roles in driving the observed variation in swap spreads. Yet, as predicted by the model, demand plays a more important role in shaping the expected returns on swap spread arbitrage, which embed a premium for bearing future demand-supply imbalance risk. Hedging activity from mortgage investors seems to play a key role in driving the demand for swaps. By contrast, the supply of swaps is closely linked to proxies for the tightness of dealers' constraints. Finally, our analysis helps explain the relationship between swap spreads and other no-arbitrage violations.
    Keywords: limits to arbitrage; intermediary capital constraints; swap spreads; covered interest parity
    JEL: G12 E43
    Date: 2022–04–05
  13. By: Van Tassell, Gerald H.; Walters, Cory G.; Preston, Richard K.; Mallory, Mindy L.
    Keywords: Risk and Uncertainty, Agricultural Finance, Research Methods/Statistical Methods
    Date: 2023
  14. By: Shuo Han; Yinan Chen; Jiacheng Liu
    Abstract: Market traders often engage in the frequent transaction of volatile assets to optimize their total return. In this study, we introduce a novel investment strategy model, anchored on the 'lazy factor.' Our approach bifurcates into a Price Portfolio Forecasting Model and a Mean-Variance Model with Transaction Costs, utilizing probability weights as the coefficients of laziness factors. The Price Portfolio Forecasting Model, leveraging the EXPMA Mean Method, plots the long-term price trend line and forecasts future price movements, incorporating the tangent slope and rate of change. For short-term investments, we apply the ARIMA Model to predict ensuing prices. The Mean-Variance Model with Transaction Costs employs the Monte Carlo Method to formulate the feasible region. To strike an optimal balance between risk and return, equal probability weights are incorporated as coefficients of the laziness factor. To assess the efficacy of this combined strategy, we executed extensive experiments on a specified dataset. Our findings underscore the model's adaptability and generalizability, indicating its potential to transform investment strategies.
    Date: 2023–06
  15. By: David Hirshleifer; Dat Mai; Kuntara Pukthuanthong
    Abstract: A war-related factor model derived from textual analysis of media news reports explains the cross section of expected asset returns. Using a semi-supervised topic model to extract discourse topics from 7, 000, 000 New York Times stories spanning 160 years, the war factor predicts the cross section of returns across test assets derived from both traditional and machine learning construction techniques, and spanning 138 anomalies. Our findings are consistent with assets that are good hedges for war risk receiving lower risk premia, or with assets that are more positively sensitive to war prospects being more overvalued. The return premium on the war factor is incremental to standard effects.
    JEL: G0 G02 G1 G10 G11 G4 G41
    Date: 2023–06
  16. By: Masood Tadi; Jiří Witzany
    Abstract: This research introduces a novel pairs trading strategy based on copulas for cointegrated pairs of cryptocurrencies. To identify the most suitable pairs, the study employs linear and non-linear cointegration tests along with a correlation coefficient measure and fits different copula families to generate trading signals formulated from a reference asset for analyzing the mispricing index. The strategy's performance is then evaluated by conducting back-testing for various triggers of opening positions, assessing its returns and risks. The findings indicate that the proposed method outperforms buy-and-hold trading strategies in terms of both profitability and risk-adjusted returns.
    Keywords: Capital ratio, Basel capital requirements, COVID-19 pandemic, global financial crisis
    JEL: C33 G21 G28
    Date: 2023–05–03
  17. By: Philippe de Donder (TSE-R - Toulouse School of Economics - UT Capitole - Université Toulouse Capitole - UT - Université de Toulouse - EHESS - École des hautes études en sciences sociales - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement, CNRS - Centre National de la Recherche Scientifique); Marie-Louise Leroux (Département des Sciences Economiques, ESG-UQAM, Montréal, Canada); François Salanié (TSE-R - Toulouse School of Economics - UT Capitole - Université Toulouse Capitole - UT - Université de Toulouse - EHESS - École des hautes études en sciences sociales - CNRS - Centre National de la Recherche Scientifique - INRAE - Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement)
    Abstract: Advantageous selection occurs when the agents most eager to buy insurance are also the cheapest ones to insure. Hemenway (1990) links it to differences in risk-aversion among agents, implying different prevention efforts, and finally different riskinesses. We argue that it may also appear when agents share the same attitude towards risk, and in the absence of moral hazard. Using a standard asymmetric information setting satisfying a single-crossing property, we show that advantageous selection may occur when several contracts are offered, or when agents also face a non-insurable background risk, or when agents face two mutually exclusive risks that are bundled together. We illustrate this last effect in the context of life care annuities, a product bundling long-term care insurance and annuities, by constructing a numerical example based on Canadian survey data.
    Keywords: Propitious selection, Positive or negative correlation property, Contract bundling, Long-term care insurance, Annuity
    Date: 2023–05–26
  18. By: Julian H\"olzermann
    Abstract: This paper studies dynamic asset allocation with interest rate risk and several sources of ambiguity. The market consists of a risk-free asset, a zero-coupon bond (both determined by a Vasicek model), and a stock. There is ambiguity about the risk premia, the volatilities, and the correlation. The investor's preferences display both risk aversion and ambiguity aversion. The optimal investment problem can be solved in closed-form under typical market conditions. The solution shows that the investor does not hedge ambiguity but only risk, while the ambiguity only affects the speculative motives of the investor. An implementation of the optimal investment strategy shows the impact of the different sources of ambiguity. Ambiguity aversion helps to tame the highly leveraged portfolios neglecting ambiguity and leads to strategies that are more in line with popular investment advice. The solution method for the optimal investment problem is based on an extension of the martingale optimality principle.
    Date: 2023–06
  19. By: Chiara Canta; Øivind A. Nilsen; Simen A. Ulsaker; Øivind Anti Nilsen
    Abstract: This paper studies empirically the relationship between competition and risk taking in banking markets. We exploit an unique dataset providing information about all bank loans to Norwegian firms over several years. Rather than relying on observed market shares, we use the distance between bank branches and firms to measure the competitiveness of local markets. The cross-sectional and longitudinal variation in competition in local markets are used to identify the relationship between competition and risk taking, which we measure by the non-performing loans and loss provision rates of the individual banks. We find that more competition leads to more risk taking. We also examine the effects of bank competition on the availability of loans. More competition leads to lower interest rates and higher loan volumes, but also makes it more difficult for small and newly established firms to obtain a loan.
    Keywords: banking, local competition, risk taking, firm behaviour
    JEL: G21 L11 L13
    Date: 2023
  20. By: Linda S. Goldberg
    Abstract: Global liquidity refers to the volumes of financial flows—largely intermediated through global banks and non-bank financial institutions—that can move at relatively high frequencies across borders. The amplitude of responses to global conditions like risk sentiment, discussed in the context of the global financial cycle, depends on the characteristics and vulnerabilities of the institutions providing funding flows. Evidence from across empirical approaches and using granular data provides policy-relevant lessons. International spillovers of monetary policy and risk sentiment through global liquidity evolve in response to regulation, the characteristics of financial institutions, and actions of official institutions around liquidity provision. Strong prudential policies in the home countries of global banks and official facilities reduce funding strains during stress events. Country-specific policy challenges, summarized by the monetary and financial trilemmas, are partially alleviated. However, risk migration across types of financial intermediaries underscores the importance of advancing regulatory agendas related to non-bank financial institutions.
    Keywords: global liquidity; global dollar cycle; trilemma; exchange market pressure; risk sensitivity; safe haven; capital flows; non-bank financial intermediaries; risk migration
    JEL: E44 F30 G15 G18 G23
    Date: 2023–06–01
  21. By: Matt Darst; Mary Zhang
    Abstract: This note extends to private firms an analysis of the impact of macroeconomic conditions on corporate interest coverage ratios (ICRs), a measure of repayment risk developed by McCoy et al. (2020). Our analysis is complimentary. We utilize unique data on private-firm balance sheets obtained through the Federal Reserve's Comprehensive Capital Analysis and Review (CCAR) process and evaluate the impact of updated and new macroeconomic projections on the distribution and path of corporate interest coverage ratios.
    Date: 2023–05–16
  22. By: Li Lin (East China University of Science and Technology); Didier Sornette (ETH Zurich, Southern University of Science and Technology (SUSTech); Tokyo Institute of Technology, and Swiss Finance Institute)
    Abstract: We propose a formulation to construct new classes of financial price processes based on the insight that the key variable driving prices P is the earning-over-price ratio γ ≃ 1/ P, which we refer to as the earning yield and is analogous to the yield-to-maturity of an equivalent perpetual bond. This modeling strategy is illustrated with the choice for real-time γ in the form of the Cox-Ingersoll-Ross (CIR) process, which allows us to derive analytically many stylised facts of financial prices and returns, such as the power law distribution of returns, transient super-exponential bubble behavior, and the fat-tailed distribution of prices before bubbles burst. Our model sheds new light on rationalizing the excess volatility and the equity premium puzzles. The model is calibrated to five well-known historical bubbles in the US and China stock markets via a quasi-maximum likelihood method with the L-BFGS-B optimization algorithm. Using ϕ-divergence statistics adapted to models prescribed in terms of stochastic differential equations, we show the superiority of the CIR process for γt against three alternative models.
    Keywords: asset pricing, financial risks, financial bubbles, excess volatility, fat tail distribution of returns, equity puzzle, earning yield, earning-over-price.
    JEL: G01 G12
    Date: 2023–02
  23. By: Fabrizio Cipollini; Giampiero M. Gallo; Alessandro Palandri
    Abstract: We focus on the time-varying modeling of VaR at a given coverage $\tau$, assessing whether the quantiles of the distribution of the returns standardized by their conditional means and standard deviations exhibit predictable dynamics. Models are evaluated via simulation, determining the merits of the asymmetric Mean Absolute Deviation as a loss function to rank forecast performances. The empirical application on the Fama-French 25 value-weighted portfolios with a moving forecast window shows substantial improvements in forecasting conditional quantiles by keeping the predicted quantile unchanged unless the empirical frequency of violations falls outside a data-driven interval around $\tau$.
    Date: 2023–05
  24. By: Zazueta, Jorge; Zazueta-Hernández, Jorge; Heredia, Andrea Chavez
    Abstract: We provide an intuitive construction of a support vector machine (SVM) and explore the motivation behind using different tools for data classification. Beginning with linear classifiers, we build intuition on the subtlety of classification in increasingly non-linear circumstances and conclude with an example of bankruptcy prediction to illustrate the effectiveness and flexibility of support vector machines.
    Date: 2023–06–23

This nep-rmg issue is ©2023 by Stan Miles. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. 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.