Corporate Bankruptcy Prediction Models Research Articles

Corporate Bankruptcy Prediction Models: A Comparative Study for the Construction Sector in Greece

This study focuses on testing the efficiency of alternative bankruptcy prediction models (Altman, Ohlson, Zmijewski) and on assessing the possible reasons that led to the confirmation or not of the prevailing model. Data from financial statements of listed (Greek) construction companies before the economic crisis were utilized. The results showed that Altman’s main predictive model as well as the revised models have low overall predictability for all three years before bankruptcy.

Are Bankruptcy Prediction Models Effective for Predicting Ratings? An Empirical Investigation of Altman’s Model in Indian Corporate Sector

The alternative method for predicting credit ratings by employing bankruptcy prediction models is the main subject of the present article. Rating agencies utilize an extremely intricate rating methodology, which differs from agency to agency, and the ratings given by agencies are less reliable in anticipating short-term defaults and react slowly to credit events, as demonstrated by the failure of agencies during the crisis of 2008. Both credit rating assignment and bankruptcy prediction focused on the probability of default, but the methodology used by the two varies significantly: corporate bankruptcy prediction models predict the future default probability of a company as a whole, whereas credit rating only access the default risk associated with a specific instrument. Therefore, it is preferable to employ bankruptcy prediction algorithms to access a company’s future ratings. The present study used Altman’s framework in order to assess whether bankruptcy prediction models can be applied to access a company’s future ratings in advance or not and found that it can be used as an alternative method to predict the future credit ratings, which can be used by investors and banks to make better investment and lending decisions.

Comparing the Performance of Corporate Bankruptcy Prediction Models Based on Imbalanced Financial Data

Forecasts of corporate defaults are used in various fields across the economy. Several recent studies attempt to forecast corporate bankruptcy using various machine learning techniques. We collected financial information on 13 variables of 1020 companies listed on the KOSPI and KOSDAQ to capture the possibility of corporate bankruptcy. We propose a data processing method for small-sample domestic corporate financial data. We investigate the case of random sampling of non-bankrupt companies versus sampling non-bankrupt companies based on approximate entropy and optimized threshold based on AUC to address the imbalance between the number of bankrupt companies and the number of non-bankrupt companies. We compare the performance measures of corporate bankruptcy prediction models for the small sample data structured in two ways and the full dataset. The experimental results of this study contribute to the selection of an appropriate corporate bankruptcy prediction model.

A Study on Machine Learning Prediction Model for Company Bankruptcy using Features in Time Series Financial Data

Based on such methods as a discriminant analysis and logistic regression, corporate bankruptcy prediction models have been developed as a means to determine the soundness of a company’s operational status based on its financial statements. However, such analytical methods work with binary variables, and thus, as the only outcome of machine learning, the company in question is considered either likely or unlikely to go bankrupt. However, this is insufficient for business operators who would need to know the possible risk factors of a bankruptcy, allowing them to plan and implement measures to avoid any misfortunes. We have therefore developed a prediction model that not only predicts but also identifies the financial variables that can possibly drive the company to bankruptcy.

Exploring the Impact of Study Characteristics in Artificial Neural Network Corporate Bankruptcy Prediction Models: A Meta-Regression Approach

Exploring the Impact of Study Characteristics in Artificial Neural Network Corporate Bankruptcy Prediction Models: A Meta-Regression Approach

Towards a comprehensive assessment system of local government fiscal health

Understanding fiscal health, also commonly referred to as financial condition, is key to sound decision making and the proper functioning of local government. Nonetheless there is no agreed upon way to measure fiscal health. We argue that the use of a conceptual framework is essential in furthering our understanding of measuring and assessing local government fiscal health. In this study we offer a framework and a set of financial accounting indicators visualizing fiscal health on the short and long term, taking into account the existing liabilities and local government obligations towards its constituents. The study draws on the theoretical and empirical analysis of corporate bankruptcy prediction models and local government fiscal distress models. We develop a possible comprehensive set of fiscal health indicators and compare it with existing empirical studies of local government fiscal health. The model captures current performance in four solvency dimensions (cash, budget, service-level and long term) and allows for predictions of future performance, taking into account risks (predictors of possible future financial stress) and capabilities (opportunities to strengthen future financial health). We tested our model by reviewing 33 empirical studies and found that we could allocate all indicators used to the dimensions of our framework. No empirical study appears to address all dimensions. The selection of performance dimensions is partly driven by the studies’ research objectives.

A comparative analysis of the effectiveness of corporate bankruptcy prediction models based on financial ratios: Evidence from Colombia

Logit and discriminant analyses have been used for corporate bankruptcy prediction in several studies since the last century. In recent years there have been dozens of studies comparing the several models available, including the ones mentioned above and also probit, artificial neural networks, support vector machines, among others. For the first time for Colombia, this paper presents a comparative analysis of the effectiveness of several models predicting corporate bankruptcy. Such models have previously been mostly used in relation to European and North American markets, whereas here they are applied to the financial ratios of three firms located in Colombia. The main objective is to corroborate the validity of these models in terms of their ability to predict firm failure in the Latin American context, specifically for two bankrupt Colombian firms and one healthy one. The analysis is conducted using bankruptcy forecasting models widely proposed in the literature and used systematically in developed countries: the multiple discriminant analysis Z-Altman model, Korol’s two-function model and Prusak’s P2 model. In addition, the logit and decision tree models developed by T. Korol are tested.

Religion and ratio analysis: Towards an Islamic corporate liquidity measure

This paper contributes to the emerging literature on the effect of religion on corporate decision making and financial reporting. Financial statement analytical tools could violate several commands of Islamic law. Specifically, traditional liquidity ratios imply undervaluation, uncertainty, and interest bearing aspects that are strictly prohibited in Islamic law. We propose an Islamic-compliant measure of corporate liquidity. In order to validate our proposed ratio as a measure of corporate liquidity, we incorporate it in the traditional corporate bankruptcy prediction models. Our measure significantly improves the accuracy of the corporate bankruptcy prediction models of Altman (1968) Z-score and Ohlson (1980).

Religion and Ratio Analysis: Towards an Islamic Corporate Liquidity Measure

This paper contributes to the emerging literature on the effect of religion on corporate decision making and financial reporting. We argue that financial statement analytical tools could violate several commands of the Islamic law. Specifically, traditional liquidity ratios imply undervaluation, uncertainty, and interest bearing aspects that are strictly prohibited in the Islamic law. We propose an Islamic-compliant measure of corporate liquidity. In order to validate our proposed ratio as a measure of corporate liquidity, we incorporate it in the traditional corporate bankruptcy prediction models. Our measure significantly improves the accuracy of the corporate bankruptcy prediction models of Altman (1968) Z-score and Ohlson (1980).

Impact of the Czech Changing Economic Environment on Bankruptcy Models

This paper is focused on corporate bankruptcy prediction models and methods to determine whether the evaluated entity has a higher probability of bankruptcy. Consequences of corporate financial distress for other business partners can be devastating and end with an insolvency proposal. To avoid these consequences, corporations need tools to provide reliable answers. Since the 1960s plenty of models have been created but not all of them are accurate enough for the current market conditions of the Czech Republic. The Czech Republic has witnessed an increasing number of insolvency proposals since 2008. There are several reasons such as the new insolvency law, global economic crisis, entering the European Union, and completion of the economic transformation, etc. The changing economic environment necessitates of testing current methods and models because reliability can decrease over time as many studies have shown. The key question is if sufficient tools exist for predicting the level of corporate financial distress that could lead to insolvency and corporate bankruptcy. Such tools should provide reliable results and to support business decision making. On one hand we need to forecast probability of corporate bankruptcy. On the other hand, we do not want to stigmatize healthy companies by classifying them as unhealthy. The model cannot fail in either way. It must identify healthy companies as those with a low risk of bankruptcy and unhealthy entities as entities with a high risk of bankruptcy. Current conditions differ significantly from the past. Czech insolvency law but there are also problems connected with the insolvency register (Smrcka, Advances in Information Systems and Technologies, 2013). Financial data are the key input for the majority of models but their availability is less than before. Though obligated to publish, many companies do not do so, often as a consequence of a poor corporate Int Adv Econ Res (2015) 21:117–118 DOI 10.1007/s11294-014-9481-0

Performance of corporate bankruptcy prediction models on imbalanced dataset: The effect of sampling methods

Corporate bankruptcy prediction is very important for creditors and investors. Most literature improves performance of prediction models by developing and optimizing the quantitative methods. This paper investigates the effect of sampling methods on the performance of quantitative bankruptcy prediction models on real highly imbalanced dataset. Seven sampling methods and five quantitative models are tested on two real highly imbalanced datasets. A comparison of model performance tested on random paired sample set and real imbalanced sample set is also conducted. The experimental results suggest that the proper sampling method in developing prediction models is mainly dependent on the number of bankruptcies in the training sample set.

Validation the Role of Previous Information in Predicting TSE Corporation Bankruptcy

For more than 50 years, predicting corporate bankruptcy has been a critical topic of global interest resulting in significant research devoted to the development and refinement of corporate bankruptcy prediction models. However, most studies overwhelmingly concentrated on using single period's information to identify bankruptcy risks and very few studies investigated the role of previous information in prediction models. This gap induced this study to construct a rolling-logit model, which uses of present and previous information and validate its performances in predicting TSE (Taiwan Security Exchange) corporate bankruptcy. The empirical results demonstrated the rolling-logit model, compared to the benchmark model, exhibited higher overall accuracy. The successful performance was attributed to a recall mechanism which allows the model to capture previous information that measures a corporation's risks based upon consistent information across time.

ASSESSMENT OF THE PRACTICAL APPLICATION OF CORPORATE BANKRUPTCY PREDICTION MODELS

In order to accurately and objectively evaluate the performance of the company and to determine the factors influencing the company's financial condition and results of operations, it is necessary to use an integrated methodology of bankruptcy forecasting. The aim of the article is to evaluate the validity of conceptual economic principles in bankruptcy prediction models and evaluate the potential practical application of these models. To achieve the aim of the article and using comparative literature analysis and descriptive approach the summarize of corporate bankruptcy prediction models is done in the theoretical aspects, empirically tested the appropriateness of their application in real situations, assessed the dynamics of corporate bankruptcies and trends in Lithuania in 2006-2010. In order to clarify the reliability of bankruptcy prediction models as well as using current bankruptcy tendencies of Lithuanian companies the probability of bankruptcy in companies is evaluated, which usually meets at least one failing business signs: 1. the company is attributed to small and medium seized business category; 2 .According to the classification of economic activities, company is attributed to wholesale or retail trade, construction or manufacturing industry; 3. The company operates in metropolitan of Lithuania. The probability of bankruptcy is evaluated in five currently operating companies and two already bankrupted companies using Altman, Springate, Zavgren and Chesser models. After the verification of availability and application of bankruptcy prediction models in seven companies, findings show that linear discrimination model reflects the most accurate financial condition of the company. Whereas the results of logistic analysis model do not reflect the actual performance of the the company and there is no purpose to use it for bankruptcy forecasting. DOI: http://dx.doi.org/10.5755/j01.em.17.3.2106

English

In this paper, Genetic Programming (GP) technique is applied to the empirical analysis of a new geometric approach of credit risk, financial ratios and bankruptcy prediction. Utilizing financial ratios for prediction of corporate bankruptcy and identification of firms’ impending failure is indeed desirable for investors, creditors, borrowing firms, and governments. This paper presents new geometric technique for empirical analysis of credit and bankruptcy risk using financial ratios. Within this framework, we propose the use of a new ratio representation which is named Risk Box measure (RB). We demonstrate the application of this geometric approach for variable representation, data visualization and financial ratios at different stages of corporate bankruptcy prediction models based on financial balance sheet ratios. These stages are the selection of variables (predictors), accuracy of each estimation model and the representation of each model for transformed and common ratios. By the time, several methods have been attempted in the use of financial ratios on predicting bankruptcy but some of them suffer from underlying shortcomings. Recently, Genetic Programming (GP) has received great attention in academic and empirical fields of solving highly complex problems. Results of Genetic Programming (GP) as statistical classification methodology are compared for common and transformed ratios and better accuracy is obtained.   Key words: Ratios analysis, risk box, credit risk, bankruptcy prediction, genetic programming.

A novel bankruptcy prediction model based on an adaptive fuzzy k-nearest neighbor method

Bankruptcy prediction is one of the most important issues in financial decision-making. Constructing effective corporate bankruptcy prediction models in time is essential to make companies or banks prevent bankruptcy. This study proposes a novel bankruptcy prediction model based on an adaptive fuzzy k-nearest neighbor (FKNN) method, where the neighborhood size k and the fuzzy strength parameter m are adaptively specified by the continuous particle swarm optimization (PSO) approach. In addition to performing the parameter optimization for FKNN, PSO is also utilized to choose the most discriminative subset of features for prediction. Adaptive control parameters including time-varying acceleration coefficients (TVAC) and time-varying inertia weight (TVIW) are employed to efficiently control the local and global search ability of PSO algorithm. Moreover, both the continuous and binary PSO are implemented in parallel on a multi-core platform. The proposed bankruptcy prediction model, named PTVPSO-FKNN, is compared with five other state-of-the-art classifiers on two real-life cases. The obtained results clearly confirm the superiority of the proposed model in terms of classification accuracy, Type I error, Type II error and area under the receiver operating characteristic curve (AUC) criterion. The proposed model also demonstrates its ability to identify the most discriminative financial ratios. Additionally, the proposed model has reduced a large amount of computational time owing to its parallel implementation. Promisingly, PTVPSO-FKNN might serve as a new candidate of powerful early warning systems for bankruptcy prediction with excellent performance.

On the Predictability of Risk Box Approach by Genetic Programming Method for Bankruptcy Prediction

Problem statement: Theoretical based data representation is an important tool for model selection and interpretations in bankruptcy analysis since the numerical representation are much less transparent. Some methodological problems concerning financial ratios such as non-proportionality, non-asymetricity, non-scalicity are solved in this study and we presented a complementary technique for empirical analysis of financial ratios and bankruptcy risk. Approach: This study presented new geometric technique for empirical analysis of bankruptcy risk using financial ratios. Within this framework, we proposed the use of a new ratio representation which named Risk Box measure (RB). We demonstrated the application of this geometric approach for variable representation, data visualization and financial ratios at different stages of corporate bankruptcy prediction models based on financial balance sheet ratios. These stages were the selection of variables (predictors), accuracy of each estimation model and the representation of each model for transformed and common ratios. Results: We provided evidence of extent to which changes in values of this index were associated with changes in each axis values and how this may alter our economic interpretation of changes in the patterns and direction of risk components. Results of Genetic Programming (GP) models were compared as different classification models and results showed the classifiers outperform by modified ratios. Conclusion/Recommendations: In this study, a new dimension to risk measurement and data representation with the advent of the Share Risk method (SR) was proposed. Genetic programming method is substantially superior to the traditional methods such as MDA or Logistic method. It was strongly suggested the use of SR methodology for ratio analysis, which provided a conceptual and complimentary methodological solution to many problems associated with the use of ratios. Respectively, GP will provide heuristic non linear regression as a tool in providing forecasting regression for studies associated with financial data. Genetic programming as one of the modern classification method out performs by the use of modified ratios. Our new method would be a general methodological guideline associated with financial data analysis.

Corporate bankruptcy prediction models applied to emerging economies

PurposeThe paper's aim is to test the usefulness of ratio analysis to predict bankruptcy in a period of stability of an emerging economy, such as the case of Argentina in the 1990s.Design/methodology/approachFinancial profiles of 22 bankrupt and healthy companies are examined and a model is built using the multiple discriminant analysis technique, thus providing comparability with previous studies.FindingsThe set of models tested in this paper show that the financial data of Argentine companies in the 1990s do have information content, but the model to use depends on the preferences of the decision maker. Comparing models it is observed a common use of solvency ratios in terms of total assets and profitability ratios in terms of sales.Research limitations/implicationsData availability constitutes the primary limitation of this and similar studies, here is reflected in the sample size: 11 healthy and 11 bankrupt.Practical implicationsThe model can be used to assist investors, creditors, and regulators in Argentina and other emerging economies to predict business failure. The Z ′‐score model of Altman can be used for public companies in emerging economies because it pays attention to solvency indicators, but in rapid changing environment, profitability ratios should also be considered.Originality/valueThe incremental information content of profitability and solvency in predicting bankruptcy is examined and a simple and reliable failure prediction model for large Argentinean firms is developed. Also this paper offers a classification method that is publicly available to all investors and creditors interested in Argentinean companies.

Bankruptcy prediction modeling with hybrid case-based reasoning and genetic algorithms approach

One of the most important research issues in finance is building effective corporate bankruptcy prediction models because they are essential for the risk management of financial institutions. Researchers have applied various data-driven approaches to enhance prediction performance including statistical and artificial intelligence techniques, and many of them have been proved to be useful. Case-based reasoning (CBR) is one of the most popular data-driven approaches because it is easy to apply, has no possibility of overfitting, and provides good explanation for the output. However, it has a critical limitation—its prediction performance is generally low. In this study, we propose a novel approach to enhance the prediction performance of CBR for the prediction of corporate bankruptcies. Our suggestion is the simultaneous optimization of feature weighting and the instance selection for CBR by using genetic algorithms (GAs). Our model can improve the prediction performance by referencing more relevant cases and eliminating noises. We apply our model to a real-world case. Experimental results show that the prediction accuracy of conventional CBR may be improved significantly by using our model. Our study suggests ways for financial institutions to build a bankruptcy prediction model which produces accurate results as well as good explanations for these results.

Comparing the performance of market-based and accounting-based bankruptcy prediction models

Recently developed corporate bankruptcy prediction models adopt a contingent claims valuation approach. However, despite their theoretical appeal, tests of their performance compared with traditional simple accounting-ratio-based approaches are limited in the literature. We find the two approaches capture different aspects of bankruptcy risk, and while there is little difference in their predictive ability in the UK, the z-score approach leads to significantly greater bank profitability in conditions of differential decision error costs and competitive pricing regime.

Predicting corporate bankruptcy: where we stand?

PurposeThe incidence of important bankruptcy cases has led to a growing interest in corporate bankruptcy prediction models since the 1960s. Several past reviews of this literature are now either out‐of‐date or too narrowly focused. They do not provide a complete comparison of the many different approaches towards bankruptcy prediction and have also failed to provide a solution to the problem of model choice in empirical application. Seeks to address this issue.Design/methodology/approachThrough an extensive literature review, this study provides a comprehensive analysis of the methodologies and empirical findings from these models in their applications across ten different countries.FindingsThe predictive accuracies of different models seem to be generally comparable, although artificially intelligent expert system models perform marginally better than statistical and theoretical models. Individually, the use of multiple discriminant analysis (MDA) and logit models dominates the research. Given that financial ratios have been dominant in most research to date, it may be worthwhile increasing the variety of explanatory variables to include corporate governance structures and management practices while developing the research model. Similarly, evidence from past research suggests that small sample size, in such studies, should not impede future research but it may lead researchers away from methodologies where large samples are critically necessary.Originality/valueIt is hoped that this study will be the most comprehensive to‐date review of the literature in the field. The study also provides a unique ranking system, the first ever of its kind, to solve the problem of model choice in empirical application of bankruptcy prediction models.