As a hot topic, financial distress prediction (FDP), or called as corporate failure prediction, bankruptcy prediction, acts as an important role in decision-making of various areas, including: accounting, finance, business, and engineering. Since academic research on FDP has gone on for nearly eighty years, there are abundant literatures on this topic, which may appear chaotic to the researchers of the field and make them feel confused. This paper contributes to the current review researches by making a full summary, analysis and evaluation on the current literatures of FDP. The current literatures of FDP are reviewed from the following four unique aspects: definition of financial distress in the new century, FDP modeling, sampling approaches for FDP, and featuring approaches for FDP. By considering the new state-of-the-art techniques in this area, FDP modeling are classified and reviewed by the following groups: namely, modeling with pure single classifier, modeling with hybrid single classifier, modeling by ensemble techniques, dynamic FDP modeling, and modeling with group decision-making techniques. Sampling methods for FDP are classified and reviewed by the following paired groups, namely: training sampling and testing sampling, single industry sampling and cross-industry sampling, balanced sampling and imbalanced sampling. Featuring methods for FDP are categorized and reviewed by qualitative selection and combination of qualitative and quantitative selection. We comment on the current researches from the view of each category and propose further research topics. The review paper is valuable to guide research and application of the area.

Predicting financial distress and corporate failure: A review from the state-of-the-art definitions, modeling, sampling, and featuring approaches

We introduce a literature review considering articles on artificial neural networks in business published in last two decades.412 suitable articles are identified and classified according to defined methodology.We focus on date, area of interest, type of neural network, benchmark method, journal and citations.The most applied are multilayer feedforward networks with backpropagation learning performed by gradient descent algorithm.Majority (25.73%) of the examined articles were published in Expert Systems with Applications. In recent two decades, artificial neural networks have been extensively used in many business applications. Despite the growing number of research papers, only few studies have been presented focusing on the overview of published findings in this important and popular area. Moreover, the majority of these reviews were introduced more than 15 years ago. The aim of this work is to expand the range of earlier surveys and provide a systematic overview of neural network applications in business between 1994 and 2015. We have covered a total of 412 articles and classified them according to the year of publication, application area, type of neural network, learning algorithm, benchmark method, citations and journal. Our investigation revealed that most of the research has aimed at financial distress and bankruptcy problems, stock price forecasting, and decision support, with special attention to classification tasks. Besides conventional multilayer feedforward network with gradient descent backpropagation, various hybrid networks have been developed in order to improve the performance of standard models. Even though neural networks have been established as well-known method in business, there is enormous space for additional research in order to improve their functioning and increase our understanding of this influential area.

Artificial neural networks in business

The bankruptcy prediction research domain continues to evolve with many new different predictive models developed using various tools. Yet many of the tools are used with the wrong data conditions or for the wrong situation. Using the Web of Science, Business Source Complete and Engineering Village databases, a systematic review of 49 journal articles published between 2010 and 2015 was carried out. This review shows how eight popular and promising tools perform based on 13 key criteria within the bankruptcy prediction models research area. These tools include two statistical tools: multiple discriminant analysis and Logistic regression; and six artificial intelligence tools: artificial neural network, support vector machines, rough sets, case based reasoning, decision tree and genetic algorithm. The 13 criteria identified include accuracy, result transparency, fully deterministic output, data size capability, data dispersion, variable selection method required, variable types applicable, and more. Overall, it was found that no single tool is predominantly better than other tools in relation to the 13 identified criteria. A tabular and a diagrammatic framework are provided as guidelines for the selection of tools that best fit different situations. It is concluded that an overall better performance model can only be found by informed integration of tools to form a hybrid model. This paper contributes towards a thorough understanding of the features of the tools used to develop bankruptcy prediction models and their related shortcomings.

Systematic Review of Bankruptcy Prediction Models: Towards A Framework for Tool Selection

We combine features derived from financial information and managerial comments.We employ feature selection and classification using a wide range of machine learning methods.Analysts forecasts of revenues and earnings are necessary to detect fraudulent firms.Misclassification cost ratio of 1:2 is based on the loss attributable to financial statement fraud and audit fees.Interpretable Nave Bayes-based models outperform remaining methods in terms of misclassification costs. Financial statement fraud has been serious concern for investors, audit firms, government regulators, and other capital market stakeholders. Intelligent financial statement fraud detection systems have therefore been developed to support decision-making of the stakeholders. Fraudulent misrepresentation of financial statements in managerial comments has been noticed in recent studies. As such, the purpose of this study was to examine whether an improved financial fraud detection system could be developed by combining specific features derived from financial information and managerial comments in corporate annual reports. To develop this system, we employed both intelligent feature selection and classification using a wide range of machine learning methods. We found that ensemble methods outperformed the remaining methods in terms of true positive rate (fraudulent firms correctly classified as fraudulent). In contrast, Bayesian belief networks (BBN) performed best on non-fraudulent firms (true negative rate). This finding is important because interpretable ``green flag values (for which fraud is likely absent) could be derived, providing potential decision support to auditors during client selection or audit planning. We also observe that both financial statements and text in annual reports can be utilised to detect non-fraudulent firms. However, non-annual report data (analysts forecasts of revenues and earnings) are necessary to detect fraudulent firms. This finding has important implications for selecting variables when developing early warning systems of financial statement fraud.

Mining corporate annual reports for intelligent detection of financial statement fraud A comparative study of machine learning methods

We develop a model of neural networks to study the bankruptcy of US banks, taking into account the specific features of the recent financial crisis We combine multilayer perceptrons and self-organizing maps to provide a tool that displays the probability of distress up to three years before bankruptcy occurs Based on data from the Federal Deposit Insurance Corporation between 2002 and 2012, our results show that failed banks are more concentrated in real estate loans and have more provisions Their situation is partially due to risky expansion, which results in less equity and interest income After drawing the profile of distressed banks, we develop a model to detect failures and a tool to assess bank risk in the short, medium and long term using bankruptcies that occurred from May 2012 to December 2013 in US banks The model can detect 9615% of the failures in this period and outperforms traditional models of bankruptcy prediction

Bankruptcy visualization and prediction using neural networks: A study of U.S. commercial banks

Recently, research of financial distress prediction has become increasingly urgent. However, existing static models for financial distress prediction are not able to adapt to the situation that the sample data flows constantly with the lapse of time. Financial distress prediction with static models does not meet the demand of the dynamic nature of business operations. This article explores the theoretical and empirical research of dynamic modeling on financial distress prediction with longitudinal data streams from the view of individual enterprise. Based on enterprise's longitudinal data streams, dynamic financial distress prediction model is constructed by integrating financial indicator selection by using sequential floating forward selection method, dynamic evaluation of enterprise's financial situation by using principal component analysis at each longitudinal time point, and dynamic prediction of financial distress by using back-propagation neural network optimized by genetic algorithm. This model's ex-ante prediction efficiently combines its ex-post evaluation. In empirical study, three listed companies' half-year longitudinal data streams are used as the sample set. Results of dynamic financial distress prediction show that the longitudinal and dynamic model of enterprise's financial distress prediction is more effective and feasible than static model.

SFFS-PC-NN optimized by genetic algorithm for dynamic prediction of financial distress with longitudinal data streams

Financial distress prediction FDP takes important role in corporate financial risk management. Most of former researches in this field tried to construct effective static FDP SFDP models that are difficult to be embedded into enterprise information systems, because they are based on horizontal data-sets collected outside the modelling enterprise by defining the financial distress as the absolute conditions such as bankruptcy or insolvency. This paper attempts to propose an approach for dynamic evaluation and prediction of financial distress based on the entropy-based weighting EBW, the support vector machine SVM and an enterprise’s vertical sliding time window VSTW. The dynamic FDP DFDP method is named EBW-VSTW-SVM, which keeps updating the FDP model dynamically with time goes on and only needs the historic financial data of the modelling enterprise itself and thus is easier to be embedded into enterprise information systems. The DFDP method of EBW-VSTW-SVM consists of four steps, namely evaluation of vertical relative financial distress VRFD based on EBW, construction of training data-set for DFDP modelling according to VSTW, training of DFDP model based on SVM and DFDP for the future time point. We carry out case studies for two listed pharmaceutical companies and experimental analysis for some other companies to simulate the sliding of enterprise vertical time window. The results indicated that the proposed approach was feasible and efficient to help managers improve corporate financial management.

Kai-Yu He

Papers

Predicting financial distress and corporate failure: A review from the state-of-the-art definitions, modeling, sampling, and featuring approaches

SFFS-PC-NN optimized by genetic algorithm for dynamic prediction of financial distress with longitudinal data streams

The dynamic financial distress prediction method of EBW-VSTW-SVM