Bankruptcy Forecasting Research Articles

Nonlinear Relationships and Their Effect on the Bankruptcy Prediction

This study uses a generalized additive model to analyze nonlinear relationships and their effect on the bankruptcy prediction in terms of a company’s probability of default. Specifically, this study examines which of the performance indicators that are contained in a company’s annual financial statements affect nonlinearly that company’s probability of bankruptcy. Furthermore, this study examines the specific form that such nonlinear relationships take and interprets their economic relevance to predicting bankruptcy. On the basis of comprehensive data on German companies, this study shows empirically that there are statistically and economically relevant nonlinear relationships that influence the bankruptcy prediction. These nonlinear relationships are observed both below and above specific thresholds with respect to a company’s adjusted equity ratio, asset structure ratio based on tangible assets, adjusted return on assets, sales, and age. Our findings show that, to increase the accuracy of bankruptcy forecasts, it is necessary to take into account nonlinear relationships in models of bankruptcy prediction.

Logit models for predicting bankruptcy

Going into bankruptcy represents main driver of company credit risk, because of which the monitoring of doing business is considered justified. Models that forecast company's going into bankruptcy are efficient tool with whose application risk of doing business can be reduced. In the paper, the first models built on the foundations of logistic regression are presented. These models also have the biggest application in practice. Advantages and disadvantages of logit model for forecasting of bankruptcy are highlighted. Short display of logit model is incurred for concrete markets with special characteristics among which is market of Republic of Serbia too.

Прогнозирование в антикризисном управлении организацией

The relevance of scientific research in the field of crisis management due to the depressed state of the
 Russian economy, including its business sector. One of the important directions of the scientific school of the
 Department of corporate management is forecasting the development of the organization in crisis. The article
 defines the essence of anti-crisis forecasting, its objective, stages and influencing factors. Special attention
 is given to forecasting methods, their classification, selection criteria. The contribution of famous Russian
 and foreign scientists to the theory of forecasting of bankruptcy of the organization, a comparative analysis
 of the advantages and disadvantages of different methods of forecasting. The list of critical indicators of the
 probability of bankruptcy.

Bankruptcy prediction of listed companies on the Tehran Stock Exchange

Purpose Bankruptcy is the last phase of economic life of companies and has some impacts on all of the entity’s stakeholders. Thus, the prediction of bankruptcy is very important. The inherent aim of preparing and developing financial accounting information is to provide a basis for economic decision-making, and any decision requires information acquisition, processing and data analysis as well as logical and correct interpretation of information. Developing models for predicting financial crisis and comparing the capabilities of existing models can help to alert management about ongoing activities and investors about economic decision for purchase shares or granting loan facilities to companies. So, the purpose of this study is the predict bankruptcy of listed companies on the Tehran Stock Exchange. Design/methodology/approach From the statistical methods’ perspective, the present research is classified as modeling and with respect to research methodology, it is a correlative-descriptive study in which the relationship between variables is analyzed based on the research objective. Predictive variables are the best ratios of cost of goods sold, non-operating revenues, net sales, predicted earnings per share (EPS) and real EPS. Findings Prediction of corporate bankruptcy crisis is one of the vital research areas. Predictive models are means for estimating the company’s future situation. Investors and creditors are highly willing to predict the bankruptcy crisis because the high costs associated with bankruptcy crisis will spoil the economy as a whole. On the other hand, this raises concerns among owners, and they are always seeking to find ways to preserve their capital through prediction of stocks continuing operations in the future. Having knowledge about bankruptcy or non-bankruptcy of automotive parts companies makes it possible to recognize weaknesses and strengths in the companies’ current performance and to make investment decisions. Practical implications Development of financial markets and, subsequently, creation of fierce competition has resulted in bankruptcy of many companies. Investors are always looking for predicting possible bankruptcy of a firm to prevent their investments risks because bankruptcy costs are high for investors, creditors, lenders and government agencies. Hence, they are seeking ways to estimate corporate bankruptcy. For this reason, over the past four decades, bankruptcy prediction has been enumerated as a key issue in companies and consequently because of its importance, many studies have been conducted to achieve the best model to predict bankruptcy. Originality/value Bankruptcy forecast is an economically important issue in every organization and company. Financial and accounting researchers are trying to offer financial models using various combinations of financial ratios with better measuring ability for performance and dividends payments as well as company continued activities. Bankruptcy prediction models are among financial analysis techniques in which the purpose of financial analysis and bankruptcy forecasting is recognition of efficiency and management executive performances. Moreover, the analysis of stock value by shareholder is another application of such research results. Basically, shareholders are interested in knowing the future status of the companies that are going to buy. In this way, shareholders use this method of analysis to estimate future activity or inactivity of firms.

Industry and Time Specific? An Examination of Bankruptcy Forecasting

The purpose of this research is to determine whether bankruptcy forecasting models are subject to industry and time specific effects. A sample of 15,848 firms was obtained from the Compustat and CRSP databases, spanning the time period 1950 to 2013, of which 396 were bankrupt. Using five models from the literature, we evaluated whether these effects impacted on the forecasting capability of the models. We found that three of the models demonstrated varying levels of success depending on the decade and industry in question, with Altman being affected significantly. The Zmijewski model outperformed both Altman and Ohlson, and also had the lowest overall change in predictive performance. In addition, based on the results of the older models it appears that the inclusion of market information increases the volatility of model performance.

Variable Selection and Corporate Bankruptcy Forecasts

Variable Selection and Corporate Bankruptcy Forecasts

АНАЛІЗ РИЗИКУ БАНКРУТСТВА ПІДПРИЄМСТВ З ВИКОРИСТАННЯМ ЧІТКИХ ТА НЕЧІТКИХ МОДЕЛЕЙ

The study touches upon solving existing urgent problem – analysis of bankruptcy risk for Ukrainian industrial enterprises in conditions of uncertainty using classic models proposed by Altman, Davidova-Belikov as well as fuzzy logic approaches proposed by Mamdani, Tsukamoto and Larsen. The purpose of the work is in development of theory and software for estimating bankruptcy risk for industrial enterprises. The software created should also provide the possibility for effectiveness analysis for estimated forecasts and respective forecasting algorithms that were used for generating the forecasts. The study also presents the results of comparative analysis for the classic and fuzzy logic based techniques of bankruptcy forecasting of industrial enterprises. The comparison is based on studying of the first and second type errors characteristic for the classic and fuzzy forecasts. Analysis of the results achieved showed that fuzzy logic based approach provides substantially better results than the classic techniques hired. The paper also provides results of studying the bankruptcy forecasts for a series of successful enterprises and those that are close to bankruptcy. The program product created “Fuzzy inference techniques for estimation of bankruptcy level for industrial enterprises” is implemented in C# programming language using instrumentation – Microsoft Visual Studio.

Z-Score for Bankruptcy Forecasting of the Companies Producing Building Materials

The article is dedicated to developing of methodological basis for the probability of enterprises’ bankruptcyforecasting. The authors have identified the reasons of the existing bankruptcy forecasting models failure, thenecessity of models developing for companies in various industries on the basis of the existing instruments. As aresult of the multivariate discriminate analysis we offer Z-scores based on the average annual rates of change andtaking into account the peculiarities of the industry companies. The model is developed for companiesspecializing in the production of building materials, it has a high level of productivity - 90.4%.

On the Prediction of Corporate Financial Distress in the Light of the Financial Crisis: Empirical Evidence from Greek Listed Firms

This paper evaluates the impact of accounting and market-driven information on the prediction of bankruptcy for Greek firms using the discrete hazard approach. The findings show that a hazard model that incorporates three accounting ratio components of Z-score and three market-driven variables is the most appropriate model for the prediction of corporate financial distress in Greece. This model outperforms a univariate model that uses the expected default frequency (EDF) derived from the Merton distance to default model, a multivariate model that is exclusively based on accounting variables, a model that combines the EDF and accounting variables, and a multivariate model that uses only market-driven variables. Classification accuracy and bankruptcy forecast tests confirm the main results. The model is also able to sustain high long-term performance when augmenting the forecast horizon from one to two and three years.

Usage of artificial neural networks for optimal bankruptcy forecasting. Case study: Eastern European small manufacturing enterprises

Our study aims to present an optimisation method for the forecasting of bankruptcy. To this end, we elaborate and optimise an artificial neural network (ANN) which, based on the situation of real companies in Eastern Europe, can forecast bankruptcy state. After describing the network structure, the performance is evaluated. Using specific statistical methods, a statistical network optimisation is performed. The conclusion is that ANNs are extremely productive in predicting firm bankruptcy, with the forecast accuracy being higher than the accuracy obtained by traditional methods. The results are applicable at an international level, though the target group of this study contains mainly Eastern European Small Manufacturing Enterprises.

ROUGH SETS AND DISCRIMINANT ANALYSIS TECHNIQUES FOR BUSINESS DEFAULT FORECASTING

(ProQuest: ... denotes formulae omitted.)1. INTRODUCTIONMany studies have addressed the problem of bankruptcy prediction and most of them do their analysis through financial ratios. Beaver (1966) utilized t-tests to evaluate the predictive ability of various financial ratios using a pair-matched sample. In a landmark paper in the bankruptcy prediction area, Altman (1968) used multiple discriminant analysis on a pair-matched sample. Altman (1968) used five financial ratios to predict whether a company is a going concern. Altman's study is very accurate in its prediction of which companies are going to go bankrupt, and the study has held up very well even after almost 35 years.In another major study Ohlson (1980) applied logistic regression in a much larger sample that did not involve pair-matching, and he found that the four statistically significant factors for identifying the probability of failure are the size of the company, measures of financial structure, measures of performance, and measures of current liquidity.Lennox (1999) examined the causes of bankruptcy for a sample of UK listed companies for the period 1987 to 1994 and found that the most important determinants of bankruptcy are profitability, leverage, cash flow, company size, industry sector and the economic cycle. Lennox (1999) argues that well-specified logit and probit models can be more accurate for identifying failing companies than discriminant analysis.Barniv and McDonald (1999) discuss several alternative techniques to probit models and logit models for predicting company failure. In recent years, many studies have developed and examined new methods for predicting bankruptcy. For example, Hwang et al. (2007) and Cheng et al. (2010) use semi-parametric methods to predict bankruptcy. Serrano-Cinca and Gutierrez-Nieto (2013) use partial lease square discriminant analysis in bankruptcy prediction. In this context, Ravi Kumar and Ravi (2007) do a deep review of the papers issued on bankruptcy forecasting and classified them into two groups, according to the usage of statistical (like the papers cited up to now) or intelligent techniques. Within the latter, the authors distinguish the following techniques: neural networks, case-based reasoned techniques, decision trees, evolutionary approaches, operational research, rough sets, support vector machines, isotonic separation, fuzzy techniques and soft computing techniques.Within the group of the papers that use fuzzy techniques, Alam et al. (2000) propose fuzzy clustering for identifying potentially failed banks and then compared it with neural networks. De Andres et al. (2005) propose fuzzy rule based classifiers for bankruptcy prediction problem. They compare the performance of Linear Discriminant Analysis and logistic regression with multi-layer perception and fuzzy-rule based classifiers. Korol and Korodi (2011) propose a fuzzy model (that uses financial ratios as inputs) to forecast firms' bankruptcy up to three years before. Scherger et. al. (2014) focuses their analysis on a set of Small and Medium sized Enterprises (SMEs) from the construction sector. The authors simulate a fuzzy model to forecast firms' health and find out the reasons that generate problems (diseases) to it.Ravi Kumar and Ravi (2007) state that, among the intelligent techniques, the neural networks has been the most used family to solve the problem of bankruptcy prediction. For example, Lin and McClean (2000) conducted a study on distressed and non-distressed quoted companies listed on the London Stock Exchange for the last 20 years. Lin and McClean used different techniques in their studies such as discriminant analysis, logistic regression, neural networks and decision trees. They conclude that the latter and neural networks provide the best results. It must be underlined that, during last years, an important line of research that combines neural networks with fuzzy logic has raised. Papers like the ones of Chen et al. …

Financial and Payback Net for SME's

Abstract Every profit oriented company uses, calculates and evaluates various financial indicators. These indicators are used to measure the economic performance, liquidity and efficiency of the company. Even if the economic crisis is over, we need these indicators that can be used for forecast as well. These indicators and this system can help to forecast the expected problems and the liquidity issues. Each company has a complex operation therefore it is not enough only to examine the liquidity situation but a more complex system is required. Instead of bankruptcy forecasting models I would like to introduce a complex indicator system which can be used by the small- and medium enterprises. The essence of this concept is that its usage is quick and easy; so it is practical and does not require expensive software. This indicator system-model can be represented easily in a graphically way and it contains the context of the measures and goals which are examined by the financial controlling. Using the accounting statements and the financial-accounting analysis methods we gain a database which contains lots of information and indicators. The model uses the short-term indicators which are connected to the financial controlling. The selection of these indicators was based on the factor analysis and experimental learning. The aim is that these variables (factors) include the most information as possible. I modified the model and the analysed indexes to short term which are best suited to the quick diagnosis and to the approach of the financial controlling. According to the principles of the model it is important whether to review the changes these indicators quarterly, monthly or even more often during the yearly operation. The advantages of the system are the economic base; the limited number of indicators and the visuality which makes the comparison of planned and actual data easier and helps the interpretation of the variances.

Applications of the inverse infection problem on bank transaction networks

The Domingos-Richardson model, along with several other infection models, has a wide range of applications in prediction. In most of these, a fundamental problem arises: the edge infection probabilities are not known. To provide a systematic method for the estimation of these probabilities, the authors have published the Generalized Cascade Model as a general infection framework, and a learning-based method for the solution of the inverse infection problem. In this paper, we will present a case-study of the inverse infection problem. Bankruptcy forecasting, more precisely the prediction of company defaults is an important aspect of banking. We will use our model to predict these bankruptcies that can occur within a three months time frame. The network itself is built from the bank’s existing clientele for credit monitoring issues. We have found that using network models for short term prediction, we get much more accurate results than traditional scorecards can provide. We have also improved existing network models by using inverse infection methods for finding the best edge attribute parameters. This improved model was already implemented in August 2013 to OTP Banks credit monitoring process, and since then it has proven its usefulness.

Variable selection and corporate bankruptcy forecasts

We investigate the relative importance of various bankruptcy predictors commonly used in the existing literature by applying a variable selection technique, the least absolute shrinkage and selection operator (LASSO), to a comprehensive bankruptcy database. Over the 1980–2009 period, LASSO admits the majority of Campbell et al. (2008) predictive variables into the bankruptcy forecast model. Interestingly, by contrast with recent studies, some financial ratios constructed from only accounting data also contain significant incremental information about future default risk, and their importance relative to that of market-based variables in bankruptcy forecasts increases with prediction horizons. Moreover, LASSO-selected variables have superior out-of-sample predictive power and outperform (1) those advocated by Campbell et al. (2008) and (2) the distance to default from Merton’s (1974) structural model.

The Use of Discriminant Analysis to Predict the Bankruptcy of Companies Listed on the NewConnect Market

The aim of this article is to analyze and evaluate the usability of discriminant models in predicting bankruptcy for companies listed on NewConnect. This market was established in 2007 and operates as an alternative trading system next to Warsaw Stock Exchange S.A., which in practice means that its regulatory regime in relation to issuers and listed companies is not as strict as the one applicable to the main market, therefore shares of small and medium-size businesses, including start-ups, can be listed on NewConnect. In this paper, discriminant models are used to analyse the financial situation of four companies removed from trading on NewConnect due to bankruptcy, Perfect Line S.A., Promet S.A., InwazjaPC S.A. and Budostal-5 S.A. The analysis is based on three models: Altman's model for emerging markets, as well as two models of the highest predictive ability according to P. Antonowicz's research, Z7INEPAN model developed in the Polish Academy of Sciences and E. Mączyńska's model, developed by Polish scientists and adapted to the Polish economy. The results confirm that these models are a valuable tool in assessing the financial condition of enterprises and allow for bankruptcy forecasting. Their application to companies listed on NewConnect, however, may be limited due to the specific profile of these entities as most of these enterprises are in fact newly formed and therefore the existing empirical data may prove insufficient.

AdaBoost based bankruptcy forecasting of Korean construction companies

A lot of bankruptcy forecasting model has been studied. Most of them uses corporate finance data and is intended for general companies. It may not appropriate for forecasting bankruptcy of construction companies which has big liquidity. It has a different capital structure, and the model to judge the financial risk of general companies can be difficult to apply the construction companies. The existing studies such as traditional Z-score and bankruptcy prediction using machine learning focus on the companies of non-specific industries. The characteristics of companies are not considered at all. In this paper, we showed that AdaBoost (adaptive boosting) is an appropriate model to judge the financial risk of Korean construction companies. We classified construction companies into three groups – large, middle, and small based on the capital of a company. We analyzed the predictive ability of the AdaBoost and other algorithms for each group of companies. The experimental results showed that the AdaBoost has more predictive power than others, especially for the large group of companies that has the capital more than 50 billion won.

The Efficiency of Bankruptcy Forecast Models in the Hungarian SME Sector

The paper examines the efficiency of bankruptcy forecast models in the Hungarian SME sector. We also try to construct own models using discriminant-analysis, logistical regression's, and neu- ral network methods, based on a random sample, what we try to validate on a second sample. It has been proved that our own model can only be applied on the first sample with an outstand- ing result. It has also been proved that complicated statistical solutions themselves are not always applicable; there is a need for the expertise of an experienced economist. The research, of course, does not say that the bankruptcy-forecast methods used in literature have lost their trustworthiness completely. It just draws the attention to the fact that the eco- nomic circumstances of Hungarian SMEs can't be compared to that of big foreign companies. Therefore, the results of the indexes developed to the large enterprise sector cannot help accu- rate decision making in case of SMEs. Huge narrowing of the complexity of economic charac- teristics may lead to false results.

The Enterprise Creditworthiness Evaluation – By Z” Score Model

Abstract There are numerous models which are under contemporary business conditions used for assessment of creditworthiness and forecasting bankruptcy possibility of a enterprise. One of these models is Altman Z – score model. On the basis of adjustments of original model for possibility of bankruptcy forecasting, which is applicable just to enterprises with whose stocks are traded on organized market, a modified model was developed which is applicable only to enterprises with whose stocks are not traded on organized market. Altman made additional modification of model and formulated Z’’ score model that is applied on production and unproductive enterprises, as well as on enterprises that operate in developing countries. Stated models separate financially successful enterprises from those that are threatened by bankruptcy proceedings. On the basis of Z’’ score model Altman classified credit rating of enterprises and with it developed Z’’ score adjusted model. In this paper, we conducted the analyses of credit rating for 33 enterprises in restructuring and 90 enterprises that are not in restructuring, by using Z’’ score adjusted model, as well as determined possibility of occurrence of bankruptcy of enterprise on the basis of Z’ score model. Authors concluded that approximately 57% of analyzed enterprises in restructuring have the lowest credit rating, while possibility of occurrence of bankruptcy in the next two years for those enterprises is more than 90%. On the other hand, approximately 60% of enterprises which are not in restructuring have high credit rating and operate in safe zone, while approximately 6% of enterprises have the lowest credit rating with high possibility of occurrence of bankruptcy in the next two years.

Survival Analysis Employed in Predicting Corporate Failure: A Forecasting Model Proposal

In face of the current economic and financial environment, predicting corporate bankruptcy is arguably a phenomenon of increasing interest to investors, creditors, borrowing firms, and governments alike. Within the strand of literature focused on bankruptcy forecasting we can find diverse types of research employing a wide variety of techniques, but only a few researchers have used survival analysis for the examination of this issue. We propose a model for the prediction of corporate bankruptcy based on survival analysis, a technique which stands on its own merits. In this research, the hazard rate is the probability of ‘‘bankruptcy’’ as of time t, conditional upon having survived until time t. Many hazard models are applied in a context where the running of time naturally affects the hazard rate. The model employed in this paper uses the time of survival or the hazard risk as dependent variable, considering the unsuccessful companies as censured observations.

적응형 부스팅을 이용한 파산 예측 모형: 건설업을 중심으로

적응형 부스팅을 이용한 파산 예측 모형: 건설업을 중심으로