Business Failure Prediction Models Research Articles

Business failure prediction models with high and stable predictive power over time using genetic programming

This study focuses on the deterioration of the predictive power and the analysis of the predictive stability of business failure prediction models, an aspect not sufficiently analysed in previous research. Insolvency prediction is considered with three temporal horizons (1 year, 3 years and 5 years prior to failure). The Genetic Programming (GP) tool has been used to achieve prediction models with high performance and stability over time, considering a long post-learning period in the stability analysis. In addition, novel scenarios representative of actual model use are proposed and considered, as well as metrics to assess the deterioration of the models’ predictive power. The optimised GP prediction models (in the three temporal horizons) present a higher performance with respect to external references and, more importantly in relation to the objective of our study, the selected GP models substantially improve on the stability reported in previous studies, meeting the pursued requirements of degree of deterioration (less than 5%) and stability (Pearson’s coefficient of variation less than 5%). Thus, the predictions of the GP models after the learning are very stable (period 2008–2019), to a certain extent immune, with respect to their environment, responding adequately in both procyclical and countercyclical modes, all of which is particularly relevant as this period includes a strong recession and a strong recovery. This should help to increase the reliability of business failure prediction models. Moreover, the relevance of including variables other than the usual financial ratios as predictors of failure is confirmed.

Efficiency of Working Capital & Assets Management in the Function of SMEs Bankruptcy Prediction

Research Question: This research has been conducted with the aim of determining whether it is possible to generate a model that can reliably predict bankruptcy of Serbian small and medium-sized enterprises (SMEs) using Working Capital Management (WCM) and Asset Management (AM) efficiency ratios. Motivation: Motive for this research is the fact there are not many business failure prediction models related to SMEs. In addition, existing models are not focused on efficiency of the two above mentioned categories. Also, previously developed models, especially traditional and ground-breaking ones, are not necessarily aligned with accounting procedures and economic environment of all countries, which indicates the need to develop a model that is adapted for Serbian territory. Idea: The idea is to develop a model that has the ability to predict whether an entity has a tendency to initiate bankruptcy proceedings in the next year. This is useful both for external stakeholders and for SMEs’ owners themselves, as it allows them to better manage resources. Data: The research was conducted on a sample of 100 Serbian SMEs. Data for the calculation of ratio indicators is available on the Business Registers Agency webpage. Tools: The research was conducted as a combination of financial and statistical analysis instruments. Ratio indicators were used for financial analysis part, while statistical analysis was conducted in SPSS program v.26 and includes logistic (binary) regression. Findings: Results of the research indicate that AM efficiency indicators are suitable for SMEs bankruptcy prediction modelling, but also indicate that WCM ratios don’t have great contribution in bankruptcy prediction for Serbian SMEs. A model that has a classification accuracy of 79% has been developed. Contribution: This research empirically tests how selected ratio indicators support SMEs bankruptcy prediction, and therefore can be beneficial for all SMEs stakeholders, but also other researches since the research methodology is explained in details.

Business failure Prediction Models: A Review and Analysis of Literature of Listed Firms in Ghana

This paper examines the phenomenon of corporate insolvency from a developing economy perspective using data from Ghana to test the applicability of the Altman Z-score model. Drawing sample data from 16 non-distress and distressed companies listed on the Ghana Stock Exchange is tested for the Z-score to predict possible failure or insolvency. The study replicates Appiah's (2011) model to investigate different companies' results with datasets within the 2018 and 2019 financial years. The sample data revealed that 18.75% were financially distressed, 37.50% were in the grey zone making their survival uncertain, and 43.75% were safe for investment. This study contributes significantly to the literature on business failure prediction from an increasingly globalized perspective while seeking to assist investors to be cautious in the cause of making investment decisions Keywords: Business failure, Corporate Governance, Financial Distress, Z-Score DOI: 10.7176/RJFA/13-20-05 Publication date: October 31 st 2022

Extending business failure prediction models with textual website content using deep learning

Business failure prediction (BFP) is an important instrument in assessing the risk of corporate failure. While a large body of research has focused on BFP, recent research in operations research and analytics acknowledges the beneficial effect of incorporating textual data for predictive modelling. However, extant BFP research that incorporates textual company information is very scarce. Based on a dataset containing 13,571 European companies provided by the largest European data aggregator, this study investigates the added value of extending traditional BFP models with textual website content. We further benchmark various feature extraction techniques in natural language processing (i.e. the vector-space approach, neural networks-based approaches and transformers) and assess the best way of representing and integrating textual website features for BFP modelling. The results confirm that including textual website data improves BFP predictive performance, and that textual features extracted by transformers add the most value to the BFP models in this benchmark setting.

Business Failure Prediction Based on a Cost-Sensitive Extreme Gradient Boosting Machine

Business failure prediction is very important for the sustainable development of enterprises. Machine learning algorithms, especially ensemble algorithms, have shown great economic benefits in enterprise financial early warning. However, the highly imbalanced class distribution of financial risk data and the inexplainable of most machine learning-based early distress warning models limit their commercial application. To address the above limitations, we enhance the business failure prediction performance by tree-ensemble in a boosting manner. Moreover, to solve the class imbalanced issue in business failure datasets, a weighted objective function, weighted cross-entropy, is embedded into the boosted tree framework, making the weighted XGBoost a cost-sensitive business failure prediction model. Besides, to tackle the second issue, we explore the intrinsic interpretability of the proposed method by visualizing the feature importance and incorporating a partial dependence plot technique to locally interpret the individual business failure event. Experimental results on business failure datasets with different predictive horizons collected from China Security Market Accounting Research (CSMAR) database show the proposed weighted XGBoost is a good solution to reduce the error on recognizing firms in business failure. Furthermore, the visualized feature importance score and partial dependence plot result both demonstrate that the cost-sensitive tree-based ensemble can be a good tool to guide the investors in making rational as well as provide interpretable business prediction results as a reference for the policy-making of the regulators.

Majority voting ensemble with a decision trees for business failure prediction during economic downturns

Accurate business failure prediction represents an advantage for market players and is important for risk management. The purpose of this study is to develop a more accurate and stable business failure prediction model by using a majority voting ensemble method with a decision tree (DT) with experimental data on US restaurant between 1980 and 2017. According to the diversity principle and individual optimized principle, DT and logit were selected as basic learning algorithms for the voting ensemble of business failure prediction. Three models, including an entire period (EP) model, an economic downturn (ED) model, and an economic expansion (EE) model, were developed by using WEKA 3.9. The prediction accuracy of the models were 88.02% for the EP model, 80.81% for the ED model, and 87.02 % for the EE model. While the EE model revealed the market capitalization, operating cash flow after interest and dividends (OCFAID), cash conversion cycle (CCC), return on capital employed (ROCE), accumulated retained earnings, stock price, and Tobin’s Q as significant variables, the ED model exposed quite different variables such as OCFAID, KZ index, stock price, and CCC. The EP model combined most of the variables from two sub-divided models except for Tobin’s Q, stock price, and debt to equity (D/E) ratio. The contribution of the paper is twofold. First, this is the first study to comprehensively evaluate the financial and market-driven variables in the context of predicting restaurant failure, especially during economic recessions. This research has employed several accounting-based measures, market-based variables, and a macro-economic factor to improve the relevance and effectiveness of prediction models. And second, by using an ensemble model with a DT, it has improved both the interpretability of the results and the prediction accuracy.

Cost-sensitive business failure prediction when misclassification costs are uncertain: A heterogeneous ensemble selection approach

In order to assess risks associated with establishing relationships with corporate partners such as clients, suppliers, debtors or contractors, decision makers often turn to business failure prediction models. While a large body of literature has focused on optimizing and evaluating novel methods in terms of classification accuracy, recent research has acknowledged the existence of asymmetric misclassification costs associated with prediction errors and thus, advocates the usage of alternative evaluation metrics. However, these papers often assume a misclassification cost matrix to be known and fixed for both the training and the evaluation of models, whereas in reality these costs are often uncertain. This paper presents a methodological framework based upon heterogeneous ensemble selection and multi-objective optimization for cost-sensitive business failure prediction that accommodates uncertainty at the level of misclassification costs. The framework assumes unknown costs during model training and accommodates varying degrees of uncertainty during model deployment. Specifically, NSGA-II is deployed to optimize cost space resulting in a set of pareto-optimal ensemble classifiers where every learner minimizes expected misclassification cost for a specific range of cost ratios. An extensive set of experiments evaluates the method on multiple data sets and for different scenarios that reflect the extent to which cost ratios are known during model deployment. Results clearly demonstrate the ability of our method to minimize cost under the absence of exact knowledge of misclassification costs.

Development of Business Failure Prediction Model Using SmartPLS on Listed Construction Companies on Bursa Malaysia

Development of Business Failure Prediction Model Using SmartPLS on Listed Construction Companies on Bursa Malaysia

A framework for big data analytics approach to failure prediction of construction firms

This study explored use of big data analytics (BDA) to analyse data of a large number of construction firms to develop a construction business failure prediction model (CB-FPM). Careful analysis of literature revealed financial ratios as the best form of variable for this problem. Because of MapReduce’s unsuitability for iteration problems involved in developing CB-FPMs, various BDA initiatives for iteration problems were identified. A BDA framework for developing CB-FPM was proposed. It was validated by using 150,000 datacells of 30,000 construction firms, artificial neural network, AmazonElastic ComputeCloud, Apache Spark and the R software. The BDA CB-FPM was developed in eight seconds while the same process without BDA was aborted after nine hours without success. This shows the issue of not wanting to use large dataset to develop CB-FPM due to tedious duration is resolvable by applying BDA technique. The BDA CB-FPM largely outperformed an ordinary CB-FPM developed with a dataset of 200 construction firms, proving that use of larger sample size with the aid of BDA, leads to better performing CB-FPMs. The high financial and social cost associated with misclassifications (i.e. model error) thus makes adoption of BDA CB-FPMs very important for, among others, financiers, clients and policy makers.

A Review of Business Failure Prediction Models Used on Financial Distressed Companies

A Review of Business Failure Prediction Models Used on Financial Distressed Companies

Variable selection in high‐dimensional regression: a nonparametric procedure for business failure prediction

Business failure prediction models are important in providing warning for preventing financial distress and giving stakeholders time to react in a timely manner to a crisis. The empirical approach to corporate distress analysis and forecasting has recently attracted new attention from financial institutions, academics, and practitioners. In fact, this field is as interesting today as it was in the 1930s, and over the last 80 years, a remarkable body of both theoretical and empirical studies on this topic has been published. Nevertheless, some issues are still under investigation, such as the selection of financial ratios to define business failure and the identification of an optimal subset of predictors. For this purpose, there exist a large number of methods that can be used, although their drawbacks are usually neglected in this context. Moreover, most variable selection procedures are based on some very strict assumptions (linearity and additivity) that make their application difficult in business failure prediction. This paper proposes to overcome these limits by selecting relevant variables using a nonparametric method named Rodeo that is consistent even when the aforementioned assumptions are not satisfied. We also compare Rodeo with two other variable selection methods (Lasso and Adaptive Lasso), and the empirical results demonstrate that our proposed procedure outperforms the others in terms of positive/negative predictive value and is able to capture the nonlinear effects of the selected variables. Copyright © 2017 John Wiley & Sons, Ltd.

A unified framework for incorporating decision making into explanations of business failure

Purpose – The purpose of this paper is to examine how decision-maker attributes unfold to precipitate organisational failure. The analysis brings to light how key attributes such as information-processing capabilities and human capital decay interact to bring about business decline and exit. Design/methodology/approach – The study is based on an integrated review and conceptualisation of the literature. Findings – The study articulates how a set of attributes of decision makers, i.e. human capital obsolescence, powerlessness, meaninglessness and institutional linkages, contributes to organisational failure. Research limitations/implications – The paper concludes by setting out an array of strategies of learning from others’ failures. Originality/value – In spite of a growing body of research on organisational failure, scholars have placed overwhelming emphasis on ecological explanations and business failure prediction models. The study moves beyond the ecological explanations to offer a more fine-grained analysis of firm-level factors that precipitate business failure.

Bootstrap Replacement to Validate the Influence of the Economic Cycle on the Structure and the Accuracy Level of Business Failure Prediction Models

AbstractThe aim of this study was to answer the question of how the economic cycle affects the stability and efficiency of business failure prediction models, using bootstrap replacement method for validation. We analyse 2228 Spanish small and medium‐sized enterprises for the period 2001–2009, and divide it into three different phases of the economic cycle (growth, crisis, recession). We find that the structure and the ability of business failure prediction models are different according to the economic cycle. These findings are relevant for the debate on the most suitable financial ratios when developing business failure prediction models and to pose their accuracy level in these prediction models. Copyright © 2015 John Wiley & Sons, Ltd.

Business failure research: a review of the Chinese experience

In spite of a growing body of literature on business failures in China and the effects of government policy, our understanding of the current state of knowledge remains unclear. The study advances research on the subject by developing the 'four-parties' framework to review and synthesises the literature. The paper lays the groundwork for an integrated understanding of the causes and consequences of business failure. In sharp contrast with the evolution and development of western-based business failure research, much of the literature on China and the Chinese firms have focused largely on business failure prediction models by bypassing the traditional evolution from qualitative case study/story approaches to quantitative-based approaches. The study outlines the important implications and promising avenues for future research.

Inability of Gearing-Ratio as Predictor for Early Warning Systems

Abstract Background: Research in business failure and insolvency prediction provides numerous potential variables, which are in the position to differentiate between solvent and insolvent firms. Nevertheless, not all of them have the same discriminatory power, and therefore their general applicability as crisis indicators within early warning systems seems questionable. Objectives: The paper aims to demonstrate that gearing-ratio is not an appropriate predictor for firm failures/bankruptcies. Methods/Approach: The first and the second order derivatives for the gearing-ratio formula were computed and mathematically analysed. Based on these results an interpretation was given and the suitability of gearing-ratio as a discriminator within business failure prediction models was discussed. These theoretical findings were then empirically tested using financial figures from financial statements of Austrian companies for the observation period between 2008 and 2010. Results: The theoretical assumptions showed that gearing-ratio is not a suitable predictor for early warning systems. This finding was confirmed with empirical data. Conclusions: The inclusion of gearing-ratio within business failure prediction models is not able to provide early warning signals and should therefore be ignored in future model building attempts.

A Business Success Versus Failure Prediction Model for Small Businesses in Israel

With the great discrepancy in the literature as to which variables do in fact lead to success or failure of small businesses there is no theory; the Lussier 15 variable business success versus failure prediction model stands out in its accuracy that has been tested and validated already in three very different parts of the world. This study further contributes by testing the model in Israel with a sample of 205 small businesses - 101 failed and 104 successful. Results support the model’s validity in Israel, reinforcing its global validity and moving toward a theory; while demonstrating similarity of SMEs in Israel to those in other economies.

Business Bankruptcy Prediction Based on Survival Analysis Approach

This study sampled companies listed on Taiwan Stock Exchange that examined financial distress between 2003 and 2009. It uses the survival analysis to find the main indicators which can explain the business bankruptcy in Taiwan. This paper uses the Cox Proportional Hazard Model to assess the usefulness of traditional financial ratios and market variables as predictors of the probability of business failure to a given time. This paper presents empirical results of a study regarding 12 financial ratios as predictors of business failure in Taiwan. It showed that it does not need many ratios to be able to anticipate potential business bankruptcy. The financial distress probability model is constructed using Profitability, Leverage, Efficiency and Valuation ratio variables. In the proposed steps of business failure prediction model, it used detail SAS procedure. The study proves that the accuracies of classification of the mode in overall accuracy of classification are 87.93%.

On the non‐financial information's significance in the business failure models

PurposeThe purpose of this paper is to focus on the development of a business failure prediction model on a sample of small and medium‐sized firms with head offices located in the region of Castilla y León (Spain), in order to prove the significance of non‐financial information on the prediction of business failure.Design/methodology/approachIn order to reach the authors' aim, one of the most used predictive statistical methods in this field (logistic regression) is applied, in which the authors consider financial ratios and non‐financial information as potential variables to predict failure. But before developing the respective models, in order to reduce the number of variables, a principal components analysis (PCA) is first applied. Then, the achieved results with this analysis are used in the prediction step, so as to estimate the models.FindingsThe results of the predictive method show that non‐financial information, which becomes significant in the developed models, helps financial ratios to improve the ability to predict failure, so any business failure model should also consider both types of information to be accurate.Originality/valueMost of the developed business failure prediction models have used a paired sample with the same number of failed and non‐failed firms, which has the drawback of not being representative of the population from which it is chosen. In order to obtain a representative sample, a random sampling method is applied, on the basis of the population size and composition. The selected sample assures that parameter estimates are not inconsistent and biased, as the statistical methods assume.

Developing a business failure prediction model for cooperatives: Results of an empirical study in Spain

The use of statistical models to predict business failures has received considerable attention in recent decades. However, very few studies have been devoted to predicting failures of cooperative societies, which play an important social and economic role in many sectors and possess certain characteristics that distinguish them from investor-owner companies. This paper develops a statistical business failure prediction model specifically for cooperative societies and identifies the most powerful predictive variables. This is done by applying logistic regression to a sample of Spanish agricultural cooperatives with financial indicators as explanatory variables. The prediction models obtained, capable of predicting failures one or two years before they actually happen, reached an accuracy level of more than 94%. The best predictors confirmed the importance to cooperatives of having a minimum amount of capital available to ensure their financial independence, which could be put at risk by virtue of the cooperative principle of “voluntary and open membership”, especially when financial problems appear on the horizon. The importance of the results-based indicators was also shown, which could be considered as obvious, given that the objectives of cooperative societies is to obtain the greatest possible advantage from the activities carried out for their members. Key words: Business failure, cooperatives, financial indicators, logistic regression, predictive model.

A success versus failure prediction model for small businesses in Singapore

PurposeThe purpose of this paper is to examine the potential success and failure of small‐ and medium‐sized enterprises (SMEs).Design/methodology/approachAn exploratory business success versus failure (S/F) prediction model is introduced, modeled after the Lussier prediction model, using data from Singapore. Using logistic regression analysis, it is found that the Lussier model (p=0.057) and the exploratory model (p=0.047) are significant predictors of business success and failure.FindingsThe Lussier model accurately predicted 85.6 percent of the surveyed firms and explained 25 percent of the variance of contributing factors to S/F, and the exploratory model explained 86.3 and 38 percent of the same, respectively. SMEs regard the top four most important factors contributing to their business S/F as: employment, training, and the retainment of high‐quality staff members; prevalence of good products, services, and optimum timing in introducing these in the marketplace; excellent relationships with customers and availability of top managers with good leadership qualities.Research limitations/implicationsIt is surprising that while pursuing their respective business activities, the SMEs surveyed in this study regarded government policy and the availability of business finance, amongst other factors, of lesser importance compared to the above‐mentioned four broad variables.Originality/valueThis paper establishes benchmarks that could be helpful to decision makers for improving future business‐related policy formulation and research. Business leaders could pursue their goal of ensuring business successes with better personnel management and leadership training by, for example, taking more business management and leadership courses and personal development. Government public policy makers and others could utilize such a model to assess a firm's potential for success so that society could benefit via the allocation of limited resources toward higher potential firms.