Performance Of Bankruptcy Prediction Models Research Articles

Utilizing principal component analysis to enhance machine learning in bankruptcy prediction: A comparative investigation

In the global economic environment, bankruptcy prediction is essential for managing financial risks. With the advancement of machine learning techniques, accurate prediction using these methods has become a research focus. This study explores the efficiency and accuracy of improved machine learning models for bankruptcy prediction through principal component analysis (PCA). By utilizing a dataset from the banking industry in Taiwan, this paper compares the performance of PCA with and without processed data using logistic regression modeling. The research methodology includes data preprocessing, PCA downscaling, and subsequent model training and testing. The key research question is whether PCA preprocessing can significantly improve the operational efficiency and predictive accuracy of the model. It is found that the model with PCA outperforms the model without PCA in terms of processing time and accuracy. This suggests that PCA can effectively improve the performance of bankruptcy prediction models and provide a more effective tool for financial risk management. These findings provide useful insights into other areas of financial analysis using machine learning and support the value of applying PCA in predictive modeling.

Impacts of crisis on SME bankruptcy prediction models’ performance

Turbulent economic situation, changes in financial reporting, swift legislative changes, or companies’ earnings management during the COVID-19 crisis might have impacted the performance of SME bankruptcy prediction models. Due to these circumstances, the performance of existing bankruptcy prediction models might have worsened. The main aim of this study is to analyse the impact of the crisis on the performance of bankruptcy prediction models. Data from 2015 to 2019 was collected for more than 90 000 SMEs to develop prediction models for three periods – two non-crisis periods and one crisis period. One-year, two-year and three-year predictions were made for these three periods via CatBoost, LightGBM and XGBoost methods. The results of this manuscript indicate that the performance of prediction models was significantly weaker during crisis periods than the performance during non-crisis periods. The weaker performance was the most evident for one-year predictions (6.5%). The difference was slightly lower for two-year predictions (4.8%) and three-year predictions (4.1%). Since lower sensitivity levels caused worse performance during crisis periods, it can be assumed that these bankruptcies were unexpected and most probably caused by the crisis. Once the COVID-19 crisis is over, existing bankruptcy models will need to be revalidated and recalibrated.

Marketing and bankruptcy risk: the role of marketing capabilities

ABSTRACT Research has demonstrated the role of marketing actions and assets in reducing bankruptcy risk. However, firms with strong marketing assets and robust marketing budgets also fall prey to bankruptcy. Therefore, the sheer magnitude of marketing expenses and mere possession of marketing assets do not fully account for the variation in bankruptcy risk. In this paper, we propose that a firm’s marketing capability, besides its marketing assets, plays an essential role in determining its bankruptcy risk by affecting cash flow. We thereby identify conditions under which a firm’s marketing assets reduce its bankruptcy risk. Using a large longitudinal dataset of U.S. firms, we show that a combination of capabilities and assets is required to reduce bankruptcy risk. We employ machine learning to analyze the effects of marketing capability on bankruptcy. Out-of-sample validation indicates that when marketing capability is included with standard financial predictors, it improves the performance of bankruptcy prediction models. .

Impact of macroeconomic indicators on bankruptcy prediction models: Case of the Portuguese construction sector

<abstract> <p>The importance of macroeconomic indicators on the performance of bankruptcy prediction models has been a contentious issue, due in part to a lack of empirical evidence. Most indicators are primarily centered around a company's internal environment, overlooking the impact of the economic cycle on the status of the company. This research brings awareness about the combination of microeconomic and macroeconomic factors. To do this, a new model based on logistic regression was combined with principal component analysis to determine the indicators that best explained the variations in the dataset studied. The sample used comprised data from 1,832 Portuguese construction companies from 2009 to 2019. The empirical results demonstrated an average accuracy rate of 90% up until three years before the bankruptcy. The microeconomic indicators with statistical significance fell within the category of liquidity ratios, solvency and financial autonomy ratios. Regarding the macroeconomic indicators, the gross domestic product and birth rate of enterprises proved to increase the accuracy of bankruptcy prediction more than using only microeconomic factors. A practical implication of the results obtained is that construction companies, as well as investors, government agencies and banks, can use the suggested model as a decision-support system. Furthermore, consistent use can lead to an effective method of preventing bankruptcy by spotting early warning indicators.</p> </abstract>

News Sentiment in Bankruptcy Prediction Models: Evidence from Russian Retail Companies

This study is aimed at investigating the application of news sentiment analysis to bankruptcy prediction models in the context of the Russian retail sector.
 We analyse 190 companies: 95 Russian retail companies that went bankrupt in 2015-2019, and 95 non-defaulting analogue companies. This figure was attained from a larger pool of 312 companies retrieved from the Spark database on the basis of analysis of relevant financial data and further validated by the presence of pertinent news media coverage within 3 years of default date. The methodological base of this analysis is the logistic regression approach, used as a benchmark model, and several machine learning models: random forest, support vector machine, and multilayer perceptron.
 The predictor set applied consists of 34 financial variables and sentiment variables, aggregated using the ‘bag-of-words’ from a total sample of 4877 news articles, from more than 800 distinct online resource locations. We establish a set of hypotheses based on a review of existing literature in the area, and evaluate their accuracy on the basis of our technical analysis.
 Our results show that sentiment variables are statistically significant, and that adding sentiment variables improves the performance of bankruptcy prediction models. Also, the results indicate some reference characteristics of companies in terms of word-choice and descriptions in the news, indicating word choices correlated with financially stability and those correlated with financially instability.

Dynamization of bankruptcy models via indicator variables

PurposeThe purpose of this paper is to enhance the predictive power of bankruptcy prediction models by taking the past values of firms’ financial ratios as benchmark. For this purpose, the paper proposes an indicator variable expressing the time trends of financial ratios.Design/methodology/approachThe proposed measure uses the minimum and the maximum of financial ratios from the previous period as benchmarks in order to give a more complete picture about the present financial performance of firms. The most popular classification methods of bankruptcy prediction were employed: discriminant analysis, logistic regression, decision trees. Sample specific results and conclusions were avoided by applying tenfold stratified cross-validation.FindingsThe empirical results suggest that the proposed measure can increase the predictive performance of bankruptcy prediction models compared to models based solely on static financial ratios. The results gave evidence for the fact that the firms’ past financial performance is a useful benchmark for evaluating the risk of future insolvency.Originality/valueThe proposed concept is completely new to the literature and practice of bankruptcy prediction. Similar concept has not been published to date. The suggested dynamization approach has three important advantages. It is easy to compute from time series of financial ratios. It is applicable within any classifier irrespective of its mathematical background. The performance of models can be enhanced without the necessity of giving up the interpretability of bankruptcy models, so the proposed measure may play very important role in the practice of credit scoring modeling as well.

The effects of handling outliers on the performance of bankruptcy prediction models

Ratio type financial indicators are the most popular explanatory variables in bankruptcy prediction models. These measures often exhibit heavily skewed distribution because of the presence of outliers. In the absence of clear definition of outliers, ad hoc approaches can be found in the literature for identifying and handling extreme values. However, it is not clear how these different approaches can affect the predictive power of models. There seems to be consensus in the literature on the necessity of handling outliers, at the same time, it is not clear how to define extreme values to be handled in order to maximize the predictive power of models. There are two possible ways to reduce the bias originating from outliers: omission and winsorization. Since the first approach has been examined previously in the literature, we turn our attention to the latter. We applied the most popular classification methodologies in this field: discriminant analysis, logistic regression, decision trees (CHAID and CART) and neural networks (multilayer perceptron). We assessed the predictive power of models in the framework of tenfold stratified crossvalidation and area under the ROC curve. We analyzed the effect of winsorization at 1, 3 and 5% and at 2 and 3 standard deviations, furthermore we discretized the range of each variable by the CHAID method and used the ordinal measures so obtained instead of the original financial ratios. We found that this latter data preprocessing approach is the most effective in the case of our dataset. In order to check the robustness of our results, we carried out the same empirical research on the publicly available Polish bankruptcy dataset from the UCI Machine Learning Repository. We obtained very similar results on both datasets, which indicates that the CHAID-based categorization of financial ratios is an effective way of handling outliers with respect to the predictive performance of bankruptcy prediction models.

Swarm intelligence based classification rule induction (CRI) framework for qualitative and quantitative approach: An application of bankruptcy prediction and credit risk analysis

Bankruptcy prediction and credit risk analysis is one of the most significant problems in the field of accounting and financial decision making. Developing an effective classification rule induction (CRI) framework for bankruptcy prediction and credit risk analysis in appropriate time is essential to prevent the business communities from being bankrupt. Traditional statistical methods and artificial intelligence techniques play a major role to predict bankruptcy and credit risks. Most of the earlier research works were carried out on quantitative methods, while few studies have proposed on qualitative methods to improvise the performance of bankruptcy prediction models. The discovery of bankruptcy prediction in a qualitative way is an important task because it depends on the subjective knowledge of the experts. In this paper, a unified framework for qualitative and quantitative bankruptcy analysis using Ant Colony Optimization (ACO) based ant-miner algorithm is proposed. Three different natured datasets are used to present a trustworthy result. For this experiment, we have collected qualitative_bankruptcy dataset and benchmarked by UCI repository. The proposed method is successfully applied and the performance analysis prove that ant-miner method is better than existing classifiers namely Logistic Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF) and Radial Basis Function (RBF) in terms of various performance analysis factors. Furthermore, the proposed ant-miner model is found to be a more suitable method for bankruptcy prediction when compared to other traditional statistical and artificial intelligence techniques.

Methodological approach of construction business failure prediction studies: a review

Performance of bankruptcy prediction models (BPM), which partly depends on the methodological approach used to develop it, has virtually stagnated over the years. The methodological positions of BPM studies were thus investigated. Systematic review was used to search and retrieve 70 journal articles and doctoral theses. Their “general methods” and “philosophical underpinnings” were investigated using summary of findings tables and meta-analysis. “General methods” results showed positive trends in terms of techniques being used, error cost consideration and model validation, with some use of skewed data being the main drawback. For “philosophical underpinnings”, positivism paradigm was discovered to be at the core of BPM studies. This is deemed inadequate because of the need to consider industries’ dynamism, financial variables flaws and social factors which actually lead to the financial status of firms. The pragmatism paradigm using mixed method is proposed. A research design framework for executing the proposed methodology is presented. This will help BPM developers go through more rigorous and robust methodology to deliver better and more valid models. Limitations of study include not reviewing studies not reported in English language and impact of different countries’ accounting practices on ratios. Limited availability of theses’ database resulted in reviewing only four theses.

Bankruptcy Prediction Using Logit and Genetic Algorithm Models: A Comparative Analysis

One of important subjects for business and financial institutions in recent decades is bankruptcy prediction. In this study, we predict bankruptcy using both logit and genetic algorithm (GA) prediction techniques under sanctions circumstances. This study also compares the performance of bankruptcy prediction models by identifying conditions under which a model performs better to examine the relative performance of models, GA was used to classify 174 bankrupt and non-bankrupt Iranian firms listed in Tehran stock exchange for the period 2006–2014. Genetic model achieved 95 and 93.5 % accuracy rates in training and test samples, respectively; while logit model achieved only 77 and 75 % accuracy rates in training and test samples, respectively. The results suggest that two models have the capability of predicting bankruptcy and GA model is more accurate than the logit model in this regard.

The role of corporate governance in forecasting bankruptcy: Pre- and post-SOX enactment

This paper contributes to the literature by documenting the improved performance of bankruptcy prediction models after including corporate governance variables. The empirical results demonstrate better predictive power for financial bankruptcy than previous bankruptcy prediction models, particularly in the post-SOX period. Our theoretical argument emphasizes the urgent need for such improvements to the bankruptcy prediction model following the introduction of the SOX Act, with the empirical results providing intuitive economic meaning for all relevant market participants. Policymakers may consider enacting laws to include designs for corporate governance monitoring mechanisms, entrepreneurs may use this model to improve their own governance structures and compensation mechanisms to avoid financial bankruptcy, and investors may refer to it to ensure that ‘losers’ are excluded from their investment portfolios.

Comparison of Bankruptcy Prediction Models: Evidence from India

The purpose of this paper is to develop and compare the performance of bankruptcy prediction models using multiple discriminant analysis, logistic regression and neural network for listed companies in India. Accordingly bankruptcy prediction models are developed, over the three years prior to bankruptcy using financial ratios. The sample consists of 72 bankrupt and 72 non-bankrupt companies over the period 1991-2013. The results indicate that compared to multiple discriminant analysis and logistic regression, neural network has the highest classification accuracy for all the three years prior to bankruptcy. This study will be useful to financial institutions, investors, creditors and auditors to identify companies that are likely to experience bankruptcy.

Comparison and Revelation of College Students' Medical Insurance Operation Mechanism

The purpose of this paper is to develop and compare the performance of bankruptcy prediction models using multiple discriminant analysis, logistic regression and neural network for listed companies in India. Accordingly bankruptcy prediction models are developed, over the three years prior to bankruptcy using financial ratios. The sample consists of 72 bankrupt and 72 non-bankrupt companies over the period 1991-2013. The results indicate that compared to multiple discriminant analysis and logistic regression, neural network has the highest classification accuracy for all the three years prior to bankruptcy. This study will be useful to financial institutions, investors, creditors and auditors to identify companies that are likely to experience bankruptcy.

A comparison of Bayesian, Hazard, and Mixed Logit model of bankruptcy prediction

The purpose of this study is to examine the impact of the choice of cut-off points, sampling procedures, and business cycles on the forecasting accuracy of bankruptcy prediction models. A misclassification can result in an erroneous prediction resulting in prohibitive costs to firms, investors, and the economy. A salient feature of our study is that our analysis includes both parametric and nonparametric bankruptcy prediction models. A sample of firms from the Bankruptcy Research Database in the U.S. is used to evaluate the relative performance of the three most commonly used bankruptcy prediction models: Bayesian, Hazard, and Mixed Logit. Our results indicate that the choice of the cut-off point and sampling procedures affect the rankings of the three models. We show that the empirical cut-off point estimated from the training sample result in the lowest misclassification costs for all three models. When tests are conducted using randomly selected samples, and all specifications of type I costs over type II costs are taken into account, the Mixed Logit model performs slightly better than the Bayesian model and much better than the Hazard model. However, when tests are conducted across business-cycle samples, the Bayesian model has the best performance and much better predictive power in recent business cycles. This study extends recent research comparing the performance of bankruptcy prediction models by identifying under what conditions a model performs better. It also allays the concerns for a range of users groups, including auditors, shareholders, employees, suppliers, rating agencies, and creditors’ with respect to assessing corporate failure risk.

Bankruptcy Prediction Using Bayesian, Hazard, Mixed Logit and Rough Bayesian Models: A Comparative Analysis

Bankruptcy prediction has been a topic of active research for business and corporate institutions in recent times. The problem has been tackled using various models viz. Statistical, Market Based and Computational Intelligence in the past. In this work, we analyze bankruptcy using both parametric and nonparametric prediction techniques. This investigation concentrates on the impact of choice of cut off points, sampling procedures and business cycle on accuracy of bankruptcy prediction models. Misclassification can result in erroneous predictions leading to prohibitive costs to investors and economy. To test the impact of choice of cut off points and sampling procedures, four bankruptcy prediction models are examined viz. Bayesian, Hazard, Mixed Logit and Rough Bayesian techniques. To evaluate the relative performance of models, a sample of firms from Lynn M. LoPucki Bankruptcy Research Database in US is used. The choice of cut off point and sampling procedures are found to affect rankings of various models. The results indicate that empirical cut off point estimated from training sample resulted in lowest misclassification costs for all the models. Although Hazard and Mixed Logit models resulted in lower costs of misclassification in randomly selected samples, Mixed Logit model did not perform well across varying business cycles. Hazard model has highest predictive power. However, higher predictive power of Rough Bayesian and Bayesian modes when ratio of cost of Type I to cost of Type II errors is high is relatively consistent across all sampling methods. This advantage of Bayesian models may make them more attractive in current economic environment. This study also compares the performance of bankruptcy prediction models by identifying conditions under which a model performs better. It applies to a varied range of user groups including auditors, shareholders, employees, suppliers, rating agencies and creditors' concerns with respect to assessing failure risk.

Using a Bayesian Model for Bankruptcy Prediction: A Comparative Approach

The purpose of this study is to examine the impact of the choice of cut-off points, sampling procedures, and the business cycle on the accuracy of bankruptcy prediction models. Misclassification can result in erroneous predictions leading to prohibitive costs to firms, investors and the economy. To test the impact of the choice of cut-off points and sampling procedures, three bankruptcy prediction models are assessed- Bayesian, Hazard and Mixed Logit. A salient feature of the study is that the analysis includes both parametric and nonparametric bankruptcy prediction models. A sample of firms from Lynn M. LoPucki Bankruptcy Research Database in the U. S. was used to evaluate the relative performance of the three models. The choice of a cut-off point and sampling procedures were found to affect the rankings of the various models. In general, the results indicate that the empirical cut-off point estimated from the training sample resulted in the lowest misclassification costs for all three models. When tests were conducted with randomly selected samples and all specifications of Type-I costs over Type-II costs are taken into account, the results show that the Mixed Logit model performs slightly better than the Bayesian model and much better than the Hazard model. However, when tests were conducted with business-cycle samples, the Bayesian model has the best performance and much better predictive power in recent business cycles. This study extends recent research comparing the performance of bankruptcy prediction models by identifying under what conditions a model performs better. It also allays a range of user groups, including auditors, shareholders, employees, suppliers, rating agencies, and creditors’ concerns with respect to assessing failure risk.