Bankruptcy prediction using fuzzy convolutional neural networks

We propose a combined method for bankruptcy prediction based on fuzzy set qualitative comparative analysis (fsQCA) and convolutional neural networks (CNN). Currently, CNNs are being applied to various fields, and in some areas are providing higher performance than traditional models. In our proposed method, a CNN uses calibrated variables from fuzzy sets to improve performance accuracy. In addition, there are no published studies on the effect of feature selection at the input level of convolutional neural networks. Therefore, this study compares four well-known feature selection methods used in financial distress prediction, (t-test, stepdisc discriminant analysis, stepwise logistic regression and partial least square discriminant analysis) to investigate their effect on classification performance. The results show that fuzzy convolutional neural networks (FCNN) lead to better performance than when using traditional methods.     

The efficacy of red flags in predicting the SEC's targets: an artificial neural networks approach

This paper illustrates the application of artificial neural networks (ANNs) to test the ability of selected SAS No. 53 red flags to predict the targets of the SEC investigations. Investors and auditors desire to predict SEC targets because substantial losses in equity value are associated with SEC investigations. The ANN models classify the membership in target (investigated) versus control (non-investigated) firms with an average accuracy of 81%. One reason for the relative success of the ANN models is that ANNs have the ability to ‘learn’ what is important. The participants in financial reporting frauds have incentives to appear prosperous as evidenced by high profitability. In contrast to conventional statistical models with static assumptions, the ANNs use adaptive learning processes to determine what is important in predicting targets. Thus, the ANN approach is less likely to be affected by accounting manipulations. Our ANN models are biased against achieving predictive success because we use only publicly available information. The results confirm the value of red flags, i.e. financial ratios available from trial balance in conjunction with non-financial red flags such as the turnover of CEO, CFO and auditors do have predictive value. © 2000 John Wiley & Sons, Ltd.     

Price uncertainty and vertical integration: an examination of petrochemical firms

The petrochemical industry employs assets subject to temporal and site specificity. The OPEC oil price shocks of the 1970s made it difficult to write contracts covering business dealings in the industry. I use this production and economic setting as a natural experiment to test transaction cost theory. In support of the theory, I find that input price uncertainty in the 1970s positively affected the extent of vertical integration by firms into input stages. Moreover, the positive reaction of vertical integration to price uncertainty mainly occurs in transactions subject to asset specificity. I also examine price controls and market power as alternative explanations for vertical integration in the industry, but fail to find support for these hypotheses.     

The effect of banking relationships on the future of financially distressed firms

In this study I empirically examine U.S. publicly traded firms to determine the impact of banking relationships on the future of financially distressed firms. Results demonstrate that obtaining a relationship-backed loan in the six months prior to distress identification significantly increases the probability of future firm emergence from distress. However, this effect decreases as the severity of firm distress increases. These results are robust to variations in banking relationship measures and to addressing endogeneity. This study provides evidence consistent with the value of lending relationships stemming from the ease of transmission of “soft” information within the lender's organization.     

Bankruptcy prediction for Korean firms after the 1997 financial crisis: using a multiple criteria linear programming data mining approach

The main purpose of this paper is to evaluate the data mining applications, such as classification, which have been used in previous bankruptcy prediction studies and credit rating studies. Our study proposes a multiple criteria linear programming (MCLP) method to predict bankruptcy using Korean bankruptcy data after the 1997 financial crisis. The results, of the MCLP approach in our Korean bankruptcy prediction study, show that our method performs as well as traditional multiple discriminant analysis or logit analysis using only financial data. In addition, our model??s overall prediction accuracy is comparable to those of decision tree or support vector machine approaches. However, our results are not generalizable because our data are from a special situation in Korea.     

Bankruptcy prediction: the case of Japanese listed companies

This paper investigates if bankruptcy of Japanese listed companies can be predicted using data from 1992 to 2005. We find that the traditional measures, such as Altman’s (J Finance 23:589–609, 1968) Z-score, Ohlson’s (J Accounting Res 18:109–131, 1980) O-score and the option pricing theory-based distance-to-default, previously developed for the U.S. market, are also individually useful for the Japanese market. Moreover, the predictive power is substantially enhanced when these measures are combined. Based on the unique Japanese institutional features of main banks and business groups (known as Keiretsu), we construct a new measure that incorporates bank dependence and Keiretsu dependence. The new measure further improves the ability to predict bankruptcy of Japanese listed companies.     

Modeling the business risk of financially weakened firms: A new approach for corporate bond pricing

Most structural models of default risk assume that the firm's asset return is normally distributed, with a constant volatility. By contrast, this article details the properties that the process of assets should have in the case of financially weakened firms. It points out that jump-diffusion processes with time-varying volatility provide a refined and accurate perspective on the business risk dimension of default risk. Representative Arrow-Debreu state price densities (SPD) and term structures of credit spreads are then explored. The credit curves show that the business uncertainties play a major in the pricing of corporate liabilities.     

Predicting sovereign debt crises using artificial neural networks: A comparative approach

Recent episodes of financial crisis have revived interest in developing models able to signal their occurrence in timely manner. The literature has developed both parametric and non-parametric models, the so-called Early Warning Systems, to predict these crises. Using data related to sovereign debt crises which occurred in developing countries from 1980 to 2004, this paper shows that further progress can be achieved by applying a less developed non-parametric method based on artificial neural networks (ANN). Thanks to the high flexibility of neural networks and their ability to approximate non-linear relationship, an ANN-based early warning system can, under certain conditions, outperform more consolidated methods.     

新破产法背景下会计师事务所的业务机会

《中华人民共和国企业破产法》已于今年6月1日起正式实施。新破产法规定,会计师事务所等社会中介机构将成为破产管理人法定主体。最高人民法院根据授权又先后制定发布了两个司法解释,对中介机构申请进入管理人名册、接受业务等事项做了明确规定。为便于广大注册会计师及时了解和掌握有关内容,更好地参与和介入破产管理人业务,我刊约请有关专家从不同角度分析介绍《企业破产法》的制定背景、核心内容以及会计师事务所介入破产业务的有关操作实务问题,分两期刊发。     

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.     

Portfolio creation using artificial neural networks and classification probabilities: a Canadian study

Financial Markets and Portfolio Management - This study aims to verify whether using artificial neural networks (ANNs) to establish classification probabilities generates portfolios with higher...     

A Re–examination of the Effectiveness of the Bankruptcy Process

As an increasing number of companies go bankrupt, society grows concerned with the process's efficacy. In contrast to previous research, we find that relatively healthy companies emerge from bankruptcy as evidenced by their operating and equity performance post bankruptcy. While we find a substantial degree of variation in the forecast accuracy of sales, EBIT and net income, we find that forecast errors are not statistically significant and are smaller than had been thought. We provide evidence to support the argument that the economy's health affects operating and equity outcomes post bankruptcy.     

A predictive system integrating intrinsic mode functions,artificial neural networks,and genetic algorithms for forecasting S&P500 intra‐day data

There is an abundant literature on the design of intelligent systems to forecast stock market indices. In general, the existing stock market price forecasting approaches can achieve good results. The goal of our study is to develop an effective intelligent predictive system to improve the forecasting accuracy. Therefore, our proposed predictive system integrates adaptive filtering, artificial neural networks (ANNs), and evolutionary optimization. Specifically, it is based on the empirical mode decomposition (EMD), which is a useful adaptive signal‐processing technique, and ANNs, which are powerful adaptive intelligent systems suitable for noisy data learning and prediction, such as stock market intra‐day data. Our system hybridizes intrinsic mode functions (IMFs) obtained from EMD and ANNs optimized by genetic algorithms (GAs) for the analysis and forecasting of S&P500 intra‐day price data. For comparison purposes, the performance of the EMD‐GA‐ANN presented is compared with that of a GA‐ANN trained with a wavelet transform's (WT's) resulting approximation and details coefficients, and a GA‐general regression neural network (GRNN) trained with price historical data. The mean absolute deviation, mean absolute error, and root‐mean‐squared errors show evidence of the superiority of EMD‐GA‐ANN over WT‐GA‐ANN and GA‐GRNN. In addition, it outperformed existing predictive systems tested on the same data set. Furthermore, our hybrid predictive system is relatively easy to implement and not highly time‐consuming to run. Furthermore, it was found that the Daubechies wavelet showed quite a higher prediction accuracy than the Haar wavelet. Moreover, prediction errors decrease with the level of decomposition.     

Desired attributes of public accounting firms in the job selection process: an empirical examination of accounting graduates' perceptions

The purpose of this study is to identify attributes of public accounting firms that accounting graduates find most desirable in their job selection decisions, and the impacts of individual differences on these perceptions. Factor analysis performed on the responses of 167 final-year accounting students in Hong Kong to a 30-item questionnaire identified seven factors. The results indicate that accounting graduates considered help in finishing their professional accounting examinations and good staff relationships as the most important criteria in their choice of employers. In addition, female accounting graduates were more concerned about the possibility of being required to travel or be transferred, but were less concerned about the reputation and profile (such as the client base and the size) of the firms than their male counterparts. Accounting graduates with a higher grade point average (GPA) were less concerned about the working environment, but more concerned about a firms' reputation and profile than those with a lower GPA. The implications of these results are discussed.     

Assessing the effectiveness of Covid-19 financial product innovations in supporting financially distressed firms and households in the UAE

Journal of Financial Services Marketing - Covid-19 has affected the global economy, influencing firm and household financial decisions worldwide. The Central Bank of the United Arab Emirates...     

A comparison of the relative costs of financial distress models: artificial neural networks,logit and multivariate discriminant analysis

This study uses two artificial neural networks (ANNs), categorical learning/instar ANNs and probabilistic (PNN) ANNs, suitable for classification and prediction type issues, and compares them to traditional multivariate discriminant analysis (MDA) and logit to examine financial distress one to three years prior to failure. The results indicate that traditional MDA and logit perform best with the lowest overall error rates. However, when the relative error costs are considered, the ANNs perform better than traditional logit or MDA. Also, as the time period moves farther away from the eventual failure date, ANNs perform more accurately and with lower relative error costs than logit or MDA. This supports the conclusion that for auditors and other evaluators interested in early warning techniques, categorical learning network and probabilistic ANNs would be useful. © 1997 John Wiley & Sons, Ltd.     

Returns to acquirers of privatizing financial services firms: An international examination

While the literature reports improved performance for privatizing firms, banking markets are different. Many privatizing financial services firms face unique problems such as an overhang of problem loans and weak credit cultures and legal systems. We investigate the returns to successful bidders in privatization acquisitions of financial services firms, examine short-horizon performance, and test whether such acquisitions result in a change in risk for the bidding firm. Our results show that the cumulative abnormal returns to shareholders of bidding firms are positive, perhaps reflecting initial optimism that the foreign firm acquiring the privatizing firm would share in the success associated with privatization. Bidders also experience an increase in their total risk following the acquisition.     

Combining conditional volatility forecasts using neural networks: an application to the EMS exchange rates

The present paper examines the out-of-sample forecasting performance of four conditional volatility models applied to the European Monetary System (EMS) exchange rates. In order to provide improved volatility forecasts, the four models’ forecasts are combined through simple averaging, an ordinary least squares model, and an artificial neural network. The results support the EGARCH specification especially after the foreign exchange crisis of August 1993. The superiority of the EGARCH model is consistent with the nature of the EMS as a managed float regime. The ANN model performed better during the August 1993 crisis especially in terms of root mean absolute prediction error.     

Artificial neural networks with feature transformation based on domain knowledge for the prediction of stock index futures

A feature transformation method based on domain knowledge for arti?cial neural networks (ANNs) is proposed. The method of feature transformation based on domain knowledge converts continuous values into discrete values in accordance with the knowledge of experts in speci?c application domains. This approach effectively ?lters data, trains the classi?er, and extracts the rules from the classi?er. In addition, it reduces the dimensionality of the feature space, which not only decreases the cost and time in the operation but also enhances the generalizability of the classi?er. The experimental results of the proposed approach will be compared and tested statistically with the results of the linear transformation method. The results show that the method of feature transformation based on domain knowledge outperforms the linear transformation in modelling of ANNs. Copyright © 2004 John Wiley & Sons, Ltd.     

Informative or distracting: CSR disclosure of peer firms and analyst forecast accuracy

We investigate the relationship between the CSR disclosure of peer firms and the analyst forecast accuracy of the focal firm. We find a negative association between peer CSR disclosure and analyst forecast error of the focal firm, indicating that peer CSR disclosure is informative. This negative association is more pronounced when the information environment of the focal firm is worse, when the correlation in fundamentals between the focal firm and its peers is higher, when the business of the focal firm is less complex, when the focal firm has more expert analyst coverage, when the focal firm's financial performance is more sensitive to CSR engagement, or when the quality of peer CSR disclosure is higher. Overall, we show that peer CSR disclosure conveys value-relevant information about the focal firm. Our study enriches the literature on both analyst forecasts and peer information, and we also provide important implications for practitioners in understanding the role of CSR disclosure in capital markets.