Feature selection methods involving support vector machines for prediction of insolvency in non‐life insurance companies

We propose two novel approaches for feature selection and ranking tasks based on simulated annealing (SA) and Walsh analysis, which use a support vector machine as an underlying classifier. These approaches are inspired by one of the key problems in the insurance sector: predicting the insolvency of a non‐life insurance company. This prediction is based on accounting ratios, which measure the health of the companies. The approaches proposed provide a set of ratios (the SA approach) and a ranking of the ratios (the Walsh analysis ranking) that would allow a decision about the financial state of each company studied. The proposed feature selection methods are applied to the prediction the insolvency of several Spanish non‐life insurance companies, yielding state‐of‐the‐art results in the tests performed. Copyright © 2005 John Wiley & Sons, Ltd.     

Bankruptcy prediction of financially stressed firms: an examination of the predictive accuracy of artificial neural networks

This is an extension of prior studies that have used artificial neural networks to predict bankruptcy. The incremental contribution of this study is threefold. First, we use only financially stressed firms in our control sample. This enables the models to more closely approximate the actual decision processes of auditors and other interested parties. Second, we develop a more parsimonious model using qualitative ‘bad news’ variables that prior research indicates measure financial distress. Past research has focused on the ‘usefulness’ of accounting numbers and therefore often ignored non‐accounting variables that may contribute to the classification accuracy of the distress prediction models. In addition, rather than use multiple financial ratios, we include a single variable of financial distress using the Zmijewski distress score that incorporates ratios measuring profitability, liquidity, and solvency. Finally, we develop and test a genetic algorithm neural network model. We examine its predictive ability to that of a backpropagation neural network and a model using multiple discriminant analysis. The results indicate that the misclassification cost of the genetic algorithm‐based neural network was the lowest among the models. Copyright © 2001 John Wiley & Sons, Ltd.     

A Comparison of Neural Network, Statistical Methods, and Variable Choice for Life Insurers' Financial Distress Prediction

This study examines the effect of the statistical/mathematical model selected and the variable set considered on the ability to identify financially troubled life insurers. Models considered are two artificial neural network methods (back‐propagation and learning vector quantization (LVQ)) and two more standard statistical methods (multiple discriminant analysis and logistic regression analysis). The variable sets considered are the insurance regulatory information system (IRIS) variables, the financial analysis solvency tracking (FAST) variables, and Texas early warning information system (EWIS) variables, and a data set consisting of twenty‐two variables selected by us in conjunction with the research staff at TDI and a review of the insolvency prediction literature. The results show that the back‐propagation (BP) and LVQ outperform the traditional statistical approaches for all four variable sets with a consistent superiority across the two different evaluation criteria (total misclassification cost and resubstitution risk criteria), and that the twenty‐two variables and the Texas EWIS variable sets are more efficient than the IRIS and the FAST variable sets for identification of financially troubled life insurers in most comparisons.     

Predicting Private Company Failures in Italy Using Financial and Non‐financial Information

The study assesses the use of non‐financial information in predicting financial distress in private companies by developing credit risk models tailored to Italian private companies. The in‐sample and out‐of‐sample prediction test results are indicative of the incremental predictive ability of the two new non‐financial variables, that is, number of shareholders and number of subsidiaries, over accounting ratios and other widely used non‐financial information, including firm age and industry dummies. To be more specific, number of shareholders and number of subsidiaries are negatively associated with private company failures, and the models augmented by the two non‐financial variables improve forecasting performance from acceptable discrimination to excellent discrimination over one‐ to three‐year time horizons.     

Empirical Evidence on the Value of Group‐Level Financial Information in Insurer Solvency Surveillance

The existing empirical research on insurer insolvency relies almost exclusively upon individual insurance company financial data, even though the insurance industry is dominated by group‐affiliated firms. This is the first study to evaluate the benefit of using group‐level data to predict insurer insolvencies for group‐affiliated insurers. The study uses financial ratios from the NAIC FAST scoring system, measured at both the company level and group level, as potential predictor variables. The results indicate that group‐level financial information substantially improves the predictive power of an insolvency prediction model relative to a model that uses only the analogous company‐level variables. In fact, the group‐level variables are found to often be substantially more powerful than company‐level variables in predicting individual insurer insolvencies. These results suggest that future insolvency analysis should, whenever feasible, include group‐level information to obtain higher predictive accuracy.     

An empirical study of the usefulness of accounting ratios to describe levels of insolvency risk

This study aims to explore the usefulness of accounting ratios to describe levels of insolvency risk. Previous studies have used the statistical technique of discriminant analysis to derive models for preducting whether a firm will or will not fail. This study will use the same statistical technique but with three differences (a) the ratios to be used in the discriminant analysis are selected by a method which ensures that no arbitrary limit is placed on their number, (b) because the significance of accounting ratios can vary from industry to industry, four industries are separately analysed; manufacturing, retail, property and finance, (c) the statistical probabilities yielded by the analysis are used to measure a firm's current level of insolvency risk. The study is concluded by interpreting the characteristic patterns of insolvency risk which emerge; an analysis of the factors causing the differences in these patterns throws new light on the causes, symptoms, and remedies of financial distress     

Bankruptcy prediction: Application of the Taylor's expansion in logistic regression

The purpose of the present study is to test whether Taylor's series expansion can be used to solve the problem associated with the functional form of bankruptcy prediction models. To avoid the problems associated with the normality of variables, the logistic model to describe the insolvency risk is applied. Taylor's expansion is then used to approximate the exponent of the logistic function, or the logit. The cash to total assets, cash flow to total assets, and shareholder's equity to total assets ratios operationalize the factors affecting the insolvency risk. The usefulness of Taylor's model in bankruptcy prediction is evaluated applying the logistic regression model to the data from the Compustat database. The classification accuracy in the test data for the first and second years before bankruptcy show that the classification accuracy of a simple financial ratio model can be increased using the second-order and interaction terms of these ratios. However, in the third year, for the test data, Taylor's expansion is not able to increase the classification accuracy when compared with the first-order model.     

A Note on Selecting a Response Measure for Financial Distress

Since 1966, researchers have examined financial distress prediction models to determine the usefulness of accounting information to lenders. These researchers primarily used legal bankruptcy as the response variable for economic financial distress, or included legal bankruptcy with other events in dichotomous prediction models. However, theoretical models of financial distress normally define financial distress as an economic event, the inability to pay debts when due (insolvency). This study uses a loan default/accommodation response variable as a proxy for the inability to pay debts when due. The purpose of this note is to empirically test whether or not using the inability of a firm to pay debts when due, loan default/accommodation, as a response measure produces different results than using legal bankruptcy as the response measure. The study's empirical results show that legal bankruptcy and loan default/accommodation financial distress prediction models produce different statistical results, thus suggesting that the responses measure different constructs. A loan default/accommodation model also fits the data better than a bankrupt model. Our results suggest that a loan default/accommodation response may be a more appropriate measure to determine which accounting information is most useful to lenders in evaluating a firm's credit risk.     

Using a hybrid evolution approach to forecast financial failures for Taiwan-listed companies

Bankruptcy has been an important topic in finance and accounting research for a long time. Recent major bankruptcies have included seemingly robust companies such as Enron, Kmart, Global Crossing, WorldCom, and Lehman Brothers. These cases have become of serious public concern due to the huge influence these companies have on the real economy. This research proposes a hybrid evolution approach to integrate particle swarm optimization (PSO) with the support vector machine (SVM) technique for the purpose of predicting financial failures. The preparation phase collected an initial sample of 68 companies listed by the Taiwan Stock Exchange Corporation (TSEC). The financial datasets were constructed based on 33 financial ratios, four non-financial ratios and one combined macroeconomic index. To select suitable indicators for the input vector, the principle component analysis (PCA) technique was applied to reduce the data and determine how groupings of indicators measure the same concept. In the swarming phase, PSO was applied to obtain suitable parameters for SVM modeling without reducing the classification accuracy rate. In the modeling phase, the SVM model was used to build a training set that was used to calculate the model's accuracy and fitness value. Finally, these optimized parameters were used in the hybrid PSO–SVM model to evaluate the model's predictive accuracy. This paper provides four critical contributions. (1) Using the PCA technique, the statistical results indicate that the financial prediction performance is mainly affected by financial ratios rather than non-financial and macroeconomic ratios. (2) Even with the input of nearly 70% fewer indicators, our approach is still able to provide highly accurate forecasts of financial bankruptcy. (3) The empirical results show that the PSO–SVM model provides better classification accuracy (i.e. normal vs. bankrupt) than the grid search (Grid–SVM) approach. (4) For six well-known UCI datasets, the PSO–SVM model also provides better prediction accuracy than the Grid–SVM, GA–SVM, SVM, SOM, and SVR–SOM approaches. Therefore, this paper proposes that the PSO–SVM approach is better suited for predicting potential financial distress.     

The Effect of Accounting Conservatism on Corporate Investment during the Global Financial Crisis

This paper examines the effect of accounting conservatism on firm‐level investment during the 2007–2008 global financial crisis. Using a differences‐in‐differences design, we find that firms with less conservative financial reporting experienced a sharper decline in investment activity following the onset of the crisis compared to firms with more conservative financial reporting. This relationship was stronger for firms that were financially constrained, faced greater external financing needs, or had higher information asymmetry. We also find that more conservative firms experienced lower declines in both debt‐raising activity and stock performance. The evidence suggests that accounting conservatism reduces underinvestment in the presence of information frictions.     

DEBT, FOLKLORE, AND CROSS-COUNTRY DIFFERENCES IN FINANCIAL STRUCTURE

Conventional wisdom has long held that, in relationship-based economies such as Japan and Germany, corporations are able to borrow more than U.S. companies, which in turn reduces their cost of capital and gives them a competitive edge. But such folklore does not stand up to scrutiny. In Japan and Germany, large businesses do not borrow more than U.S. companies–and, in fact, judging from coverage ratios, German companies (as well as U.K. companies) seem to borrow considerably less than their international competitors.
The article also reports that, in countries where financial markets are "transparent," the development of the banking sector has little additional impact on the growth of "financially dependent" industries. That is, although industries that require a lot of external finance grow faster in countries where the bank credit-to-GDP ratio is high, the growth rates of such industries are much more correlated with the level of accounting standards (with high standards serving as a proxy for well-developed capital markets) than with a strong banking system.     

Is the Abnormal Post-IPO Underperformance Really Abnormal? The Evidence from CEE Emerging Markets

Using sorting procedures and cross-sectional tests, we investigate the long-run post-IPO performance and its sources in the Central and Eastern European (CEE) markets. We examine over 1100 stocks from 11 CEE countries for the period 2002–2014. We find that “old stocks” perform significantly better than “young stocks”, but only when the market beta is the sole risk factor considered. After accounting for the size and value effects, the IPO firms perform neither better nor worse than non-issuing companies. The sources of the initial low B/M ratios of debuting companies may lie in time-varying financial quality. The market newcomers are financially healthier than their older counterparts. However, over 2–5 years the fundamentals deteriorate and the financial standing regresses to the mean.     

Strategic Financial Management: Lessons from Seasoned Equity Offerings

Each of today's three dominant academic theories of capital structure has trouble explaining the financing behavior of companies that have seasoned equity offerings (SEOs). In conflict with the tradeoff theory, the authors’ recent studies of some 7,000 SEOs by U.S. industrial companies over the period 1970‐2017 notes that the vast majority of them—on the order of 80%—had the effect of moving the companies away from, rather than toward, their target leverage ratios. Inconsistent with the pecking‐order theory, SEO issuers have tended to be financially healthy companies with low leverage and considerable unused debt capacity. And at odds with the market‐timing theory, SEOs appear to be driven more by the capital requirements associated with large investment projects than by favorable market conditions. The authors’ findings also show that, in the years following their stock offerings, the SEO companies tend to issue one or more debt offerings, which have the effect of raising their leverage back toward their targets. Whereas each of the three theories assumes some degree of shortsightedness among financial managers, the authors’ findings suggest that long‐run‐value‐maximizing CFOs manage their capital structures strategically as opposed to opportunistically. They consider the company's current leverage in relation to its longer‐run target, its investment opportunities and long‐term capital requirements, and the costs and benefits of alternative sequences of financing transactions. This framework, which the authors call strategic financial management, aims to provide if not a unifying, then a more integrated, explanation—one that draws on each of the three main theories to provide a more convincing account of the financing and leverage decisions of SEO issuers.     

Assessing the riskiness and profitability of credit-card banks

This article measures the riskiness and profitability of financial institutions specializing in credit-card loans and related plans. Focusing on explicit accounting returns on explicit credit-card assets, we find that credit-card banks, whether subsidiaries of bank holding companies or independent banks, earned extraordinary returns over the years 1984 to 1991. On average, credit-card firms had pretax return on assets of 3.36 percent compared to .95 for noncredit-card banks. The costs of the higher returns are greater variability of ROA and higher probabilities of insolvency, indicating that credit-card banks are riskier than other commercial banks.After a decade of rapid and profitable growth, America's credit-card business is slowing down and turning cut-throat. Card companies must adap to survive.-The Economist, November 2, 1991     

Rwanda Legal Framework on Insolvency: Problems and Proposals for Reform

The purpose of this article is to explore some key insolvency issues, which will be highly selective for this article, and to identify the weaknesses and inconsistencies in the existing framework on insolvency. Rwanda does not have an efficient and effective framework on insolvency, and the article argues that there is a need for an improved insolvency law regime. In view of the weaknesses and inconsistencies, it is vital to consider international best practices such as the United Nations Commission on International Trade Law (UNCITRAL) Legislative Guide on Insolvency and the UNCITRAL Model Law on Cross‐border Insolvency as the basis needed to deal with different aspects or elements of the Rwanda insolvency law. The value of this article lies in the insights it offers into the current framework on insolvency and the opportunity given to address the inconsistencies, weaknesses and uncertainties that invariably arise from the law. Copyright © 2015 INSOL International and John Wiley & Sons, Ltd     

Detecting Accounting Fraud in Publicly Traded U.S. Firms Using a Machine Learning Approach

We develop a state-of-the-art fraud prediction model using a machine learning approach. We demonstrate the value of combining domain knowledge and machine learning methods in model building. We select our model input based on existing accounting theories, but we differ from prior accounting research by using raw accounting numbers rather than financial ratios. We employ one of the most powerful machine learning methods, ensemble learning, rather than the commonly used method of logistic regression. To assess the performance of fraud prediction models, we introduce a new performance evaluation metric commonly used in ranking problems that is more appropriate for the fraud prediction task. Starting with an identical set of theory-motivated raw accounting numbers, we show that our new fraud prediction model outperforms two benchmark models by a large margin: the Dechow et al. logistic regression model based on financial ratios, and the Cecchini et al. support-vector-machine model with a financial kernel that maps raw accounting numbers into a broader set of ratios.     

Barter Credit: Warehouses as a Contracting Technology

A large Brazilian agribusiness lender introduces a new contracting technology: grain warehouses. Using runner-up warehouse locations as a control group, I find that construction of these warehouses permits a new debt contract, namely, barter credit repayable in grain. This contract increases borrowers' debt capacity and reduces borrowing costs. The effects are stronger when grain price risk is higher, for municipalities with weaker courts, and for financially constrained borrowers. These findings are consistent with barter credit reducing financial market imperfections by mitigating borrowers' output price risk.     

Private Equity,Buy‐outs and Insolvency Risk

Private equity restructuring using debt has been criticized for increasing financial distress and bankruptcy especially following the financial crisis. We build a unique dataset comprising the population of over 9 million firm‐year observations and 153,000 insolvencies during the period 1995–2010. We compare the insolvency hazard of the spectrum of buy‐out types within the corporate population over time and investigate the risk profile of the companies pre‐buy‐out. Controlling for size, age, sector and macro‐economic conditions, private‐equity backed buy‐outs are no more prone to insolvency than non‐buy‐outs or other types of management buy‐ins. Moreover, leverage is not the characteristic that distinguishes failed buy‐outs from those surviving.     

Financial Distress in the Great Depression

We use firm‐level data to study corporate performance during the Great Depression era for all industrial firms on the NYSE. Our goal is to identify the factors that contribute to business insolvency and valuation changes during the period 1928‐1938. We find that firms with more debt and lower bond ratings in 1928 became financially distressed more frequently during the Depression, consistent with the trade‐off theory of leverage and the information production role of credit rating agencies. We also document for the first time that firms responded to tax incentives to use debt during the Depression era but that the extra debt used in response to this tax‐driven “debt bias” did not contribute significantly to the occurrence of distress. Finally, we conduct an out‐of‐sample test during the recent 2008‐2009 Recession and find that higher leverage and lower bond ratings also increased the occurrence of financial distress during this period.     

Do principles‐based accounting standards lead to biased financial reporting? An Australian experiment

International accounting standards are deliberately designed to be principles‐based (i.e. ‘substance over form’). With Australia's recent adoption of international accounting standards, a relevant question is, do principles‐based accounting standards lead to biased financial reporting? The present paper describes a study that analysed the consolidation judgements of senior accounting officials from Australian listed companies. Participants made consolidation judgements based on AASB 1024 Consolidated Accounts. Although AASB 1024 is not identical to IAS 27 Consolidated and Separate Financial Statements, there are many similarities and both follow a principles‐based approach. In aggregate, the present study finds that principles‐based accounting standards do not necessarily lead to biased financial reporting.