Bankruptcy Prediction Research Articles

EFFECTIVENESS OF THE BUSINESS FAILURE PREDICTION MODELS IN THE IBERIAN TRANSPORT COMPANIES

Purpose: validate, in the existing models, its effectiveness and ability to provide useful information for decision-making, allowing the choice of one that presented as the best alternative for predicting bankruptcy for companies in the transport economic sector (NACE H) up to 6 years before it occurs. Theoretical Framework: in the last decades, since Beaver's (1966) preliminary work in bankruptcy prediction, followed by Altman (1968) models, numerous authors developed different techniques and models to this purpose. Of all the techniques used and developed in almost 60 years of bankruptcy prediction study, Multivariate Discriminant Analysis (MDA) stands out. Despite its limitations, it best combines management and usage simplicity offering stable levels of efficiency. Design/Methodology/Approach: we selected, Portuguese and Spanish companies, from the transport and storage economic sector, subject to statutory auditing, in a sample of 22 companies, considered healthy, according to the most common criterion in the literature: Equity above zero, during six and that in the seventh were considered bankrupt (Equity below zero) and another, paired with the previous one, by Total Assets and Revenues, with 36 companies that presented Equity above zero throughout all the analyzed period, granting the analyzed models full forecasting potential. Were used 21 multi-sectorial models, for different timelines and geographies, with a greater presence in the literature, or developed by Edward Altman, a unique researcher on this subject, between 1979 and 2014. Findings: As a main conclusion, in addition to the description of models and techniques, the formulations developed by Carvalho das Neves (1998), Lizarraga (1998) and Monelos et al. (2011) were the best predictors of bankruptcy, up to 6 years before it occurs, for Portuguese and Spanish companies in the transport economic sector (NACE H). Research, Practical & Social Implications: This information can be used by any interested entity to improve current conditions, optimize and enhance the usage the bankruptcy forecast models. Originality/Value: The global financial crisis and the growing number of company closures make it crucial to understand the causes of corporate failure, with emphasis on forecasting and anticipating it.

An Enhanced Ant Colony Optimisation Algorithm with the Hellinger Distance for Shariah-Compliant Securities Companies Bankruptcy Prediction

This study addresses the challenge of applying ant colony optimisation algorithms to imbalanced datasets, focusing on a bankruptcy dataset. The application of ant colony optimization (ACO) algorithms has been limited by their performance on imbalanced datasets, particularly within bankruptcy prediction where the some of bankruptcy cases lead to skewed data distributions. Traditional ACO algorithms, including the original Ant-Miner, often fail to accurately classify minority classes, which is a critical shortcoming in the context of financial distress analysis. Hence, this study proposes an improved algorithm, the Hellinger Distance Ant-Miner (HD-AntMiner), which employs Hellinger distance as the heuristic for ants to gauge the similarity or dissimilarity between probability distributions. The effectiveness of HD-AntMiner is benchmarked against established classifiers—PART and J48—as well as the conventional Ant-Miner, using public datasets and a specialized dataset of 759 Shariah-compliant securities companies in Malaysia. Utilising the Friedman test and F-score for validation, HD-AntMiner demonstrates superior performance in handling imbalanced datasets compared to other algorithms, as affirmed by the Friedman test. The F-score analysis highlights HD-AntMiner’s excellence, achieving the highest F-score for Breast-cancer and Credit-g datasets. When applied to the Shariah-compliant dataset, HD-AntMiner is compared with Ant-Miner and validated through a t-test and F-score. The t-test results confirm HD-AntMiner’s higher accuracy than Ant-Miner, while the F-score indicates superior performance across multiple years in the Shariah-compliant dataset. Although the number of rules and conditions is not statistically significant, HD-AntMiner emerges as a robust algorithm for enhancing classification accuracy in imbalanced datasets, particularly in the context of Shariah-compliant securities prediction.

Analisis Laporan Keuangan Untuk Mengukur Kinerja Keuangan Pt. Kimia Farma pada Bursa Efek Indonesia

This research aims to see how the financial performance of PT. Kimia Farma uses liquidity and profitability ratio analysis for the 2017-2021 period, and whether PT. Kimia Farma is experiencing potential bankruptcy based on the Altman Z-Score model for the 2017-2021 period. This research uses quantitative descriptive methods. The type of data used by researchers is quantitative data and qualitative data obtained from www.idx.id. Data collection takes the form of literature study and documentation. Bankruptcy prediction calculations use the Altman Z-Score Model and profitability ratios ROA, ROE, and Net Profit Margin. The research results show that the Liquidity Ratio value of PT. Kimia Farm Ajika is measured by the Current Ratio which is in accordance with industry standards, however the company's quick ratio is still below the industry standard value. Profitability value of PT. Kimia Farma is still below industry standards due to the company's lack of minimizing costs which causes the company's profits to decrease. In calculating bankruptcy using the Altman Z-Score method, the company can be said to be good because it is still above the standard value. There are recommendations that can be used as input for PT. Kimia Farma, Tbk must further increase working capital in order to create and increase profits which will have an impact on the increase in shares and must minimize the company's operational costs.

Impact of Different Outlier Handling Techniques on GAN Based Hybrid Bankruptcy Prediction Models

Impact of Different Outlier Handling Techniques on GAN Based Hybrid Bankruptcy Prediction Models

Pengaruh Efektivitas Komite Audit, Bankruptcy Prediction, dan Solvabilitas terhadap Audit Delay

This research analyzes the influence of audit committee effectiveness, bankruptcy prediction, and solvency on audit delays. This research uses annual reports on basic material sector companies listed on the Indonesian stock exchange for 2018-2022. The sampling technique used in this research is purposive sampling, with a total sample of 70 companies in 2018-2022. This study uses multiple linear regression analysis in hypothesis testing. The results showed that audit committee. The sample selection in this study used a purposive sampling technique. The research results show that the effectiveness of the audit committee and Bankruptcy prediction do not have a significant effect on audit delay. Meanwhile, solvency has a significant effect on audit delay.

Is Artificial Intelligence Really More Accurate in Predicting Bankruptcy?

Predicting bankruptcy within selected industries is crucial because of the potential ripple effects and unique characteristics of those industries. It serves as a risk management tool, guiding various stakeholders in making decisions. While artificial intelligence (AI) has shown high success rates in classification tasks, it remains uncertain whether its use significantly enhances the potential for early warning of impending problems. The following question arises: will classical methods eventually replace the effectiveness of these advanced techniques? This paper sheds light on the fact that even classical methods continue to achieve results that are not far behind, highlighting their enduring importance in financial analysis. This paper aims to develop bankruptcy prediction models for the chemical industry in Slovakia and to compare their effectiveness. Predictions are generated using the classical logistic regression (LR) method as well as AI techniques, artificial neural networks (ANNs), support vector machines (SVMs), and decision trees (DTs). The analysis aims to determine which of the employed methods is the most efficient. The research sample consists of circa 600 enterprises operating in the Slovak chemical industry. The selection of eleven financial indicators used for bankruptcy prediction was grounded in prior research and existing literature. The results show that all of the explored methods yielded highly similar outcomes. Therefore, determining the clear superiority of any single method is a difficult task. This might be partially due to the potentially reduced quality of the input data. In addition to classical statistical methods employed in econometrics, there is an ongoing development of AI-based models and their hybrid forms. The following question arises: to what extent can these newer approaches enhance accuracy and effectiveness?

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.

Combining intra-risk and contagion risk for enterprise bankruptcy prediction using graph neural networks

Predicting the bankruptcy risk of small and medium-sized enterprises (SMEs) is crucial for making decisions about loans. Existing studies in both finance and AI research fields, however, tend to only consider either the intra-risk or contagion risk of enterprises, ignoring their interactions and combinatorial effects. This study for the first time considers both types of risk and their joint effects in bankruptcy prediction. Specifically, we first propose an enterprise intra-risk encoder based on statistically significant enterprise risk indicators for its intra-risk learning. Then, we propose an enterprise contagion risk encoder based on an enterprise knowledge graph for its contagion risk embedding. In particular, the contagion risk encoder includes both the newly proposed Heterogeneous Hyper-Graph Neural Networks (HHGNN) and Hierarchical Graph Transformer Networks (HGTN). Using these two types of encoders, we design a unified framework to simultaneously capture intra-risk and contagion risk for bankruptcy prediction. To evaluate the model, we collect real-world multi-sources data on SMEs and build a novel benchmark dataset called SMEsD. We provide open access to the dataset, which is expected to further promote research on financial risk analysis. Experiments on SMEsD against twelve state-of-the-art baselines demonstrate the effectiveness of the proposed model for bankruptcy prediction.

Bankruptcy Prediction using Diophantine Neutrosophic Number for Enterprise Resource Planning on Value of Accounting Information

Enterprise Resource Planning (ERP) is paramount in modern business, integrating many fundamental processes such as human resources, economics, customer relationship management, and supply chain management into a comprehensive infrastructure. Leveraging the wide-ranging data apprehended by ERP techniques, an organization could improve its financial analysis abilities, involving bankruptcy prediction. By using analytics methods like predictive modeling and machine learning, the ERP system could examine market trends, historical financial information, key performance indicators, and other related factors to evaluate the financial stability and health of the company. This prediction insight empowers businesses to vigorously detect advanced indicators of financial distress, alleviate risks, and make informed strategic decisions to avoid bankruptcy. Integrating bankruptcy prediction techniques within the ERP system allows organizations to reinforce contingency strategies, financial planning, and risk management, protecting long-term competitiveness and sustainability in a dynamic business environment. This study introduces a Bankruptcy Prediction using the Diophantine Neutrosophic Number for Enterprise Resource Planning (BPDNN-ERP) technique on the value of accounting information. The BPDNN-ERP technique begins with a harmony search algorithm (HSA) for electing feature subsets. In addition, the BPDNN-ERP technique applies the DNN model for the prediction of bankruptcies. To increase the performance of the DNN model, the manta ray foraging optimization (MRFO) model can be used. The experimental study demonstrated the enhanced performance of the BPDNN-ERP algorithm equated to existing forecasting methods

Financial distress predictions with Altman, Springate, Zmijewski, Taffler and Grover models

Several models have been developed to predict financial difficulties and corporate bankruptcy. In this research various models were employed, including the Altman model (referred to as the Z-Score), the Springate model (known as the S-Score), the Zmijewski model (designated as the X-Score), and the Grover model (referred to as the G-Score). These techniques serve the purpose of evaluating the likelihood of encountering financial difficulties, which in turn determines the probability of PT Garuda Indonesia (Persero) Tbk going bankrupt. The study utilized secondary data sourced from financial statements spanning the years from 2020 to 2022. The application of the Altman model for bankruptcy prediction revealed that PT Garuda Indonesia (Persero), Tbk experienced financial distress throughout the period from 2020 to 2022. According to the Springate model, the company was in a state of distress and declared bankruptcy in 2020 and 2022, while 2021 fell into a grey area. The Zmijewski model indicated that the company was on the brink of bankruptcy, with financial difficulties and a potential risk of bankruptcy within the next three years. Grover's model predicted bankruptcy for the company in 2020 and 2022, but indicated safety in 2021. Notably, the Taffler model emerged as the most accurate in forecasting bankruptcy, boasting a 100% accuracy rate with no errors. Meanwhile, the Zmijewski model achieved an 81.25% accuracy rate with an error rate of 18.75%, and the Springate model exhibited the lowest accuracy in bankruptcy prediction, scoring only 12.50% accuracy with an error rate of 87.50%.

Artificial intelligence applications in auditing processes in the banking sector

This research provides an in-depth examination of the role artificial intelligence (AI) plays in revolutionizing bank auditing and quality control processes. By integrating AI technologies, the banking industry stands on the edge of a transformative era where the efficiency, accuracy, and security of auditing operations are significantly enhanced. This systematic mapping study (SMS) explores the extent of AI’s adoption in bank audits, specific areas of its application, its impact on auditing processes, challenges, and the dynamics of human-AI collaboration in auditing. The findings reveal AI’s pivotal roles in enhancing credit risk analysis, operational efficiency, fraud detection, cybersecurity, and bankruptcy prediction, through analyzing complex data, identifying patterns, and ensuring financial stability, which leads to streamlining operations, detecting fraudulent activities through advanced pattern recognition, boosting cybersecurity measures, and accurately forecasting bankruptcy risks, thereby offering a robust tool for risk management and decision-making in the banking sector. By filling a critical gap in the literature, the study advances our understanding of AI’s capabilities, limitations, ethical considerations of AI integration, and the need for further research to overcome technological challenges and ethical dilemmas. The comprehensive analysis offers valuable insights for academic debate, businesses, and regulators to enhance the quality, efficiency, and security of financial auditing practices in the digital age.

Financial distress analysis for the prediction of corporate bankruptcy – a case study of a public sector company in India

Purpose: the present study examines the liquidity of the firm and its impact on financial distress, which may or may not increase the chances of bankruptcy. The study also analyzes the profitability, cash position, and solvency of the firm. Design/methodology/approach: we use the data of a listed Government manufacturing company and measure the financial distress and probabilities of bankruptcy to test the chances of financial distress during the period between 2015 and 2019. The financial models used for evaluation in the study are the Altman z-score model, Logit Probability model, and Falmur model. Findings: The study found that there was a chance of bankruptcy in the initial years, but later, it survived the bankruptcy. The study also established that the liquidity and solvency of the firm were not up to the standard. Practical implications: the result of the study extends our theoretical understanding and also provides valuable guidelines to reduce the chance of insolvency, bankruptcy, and financial distress of firms and to maintain the proper financial health of the firm. Originality/value: while many empirical studies investigate the relationship between liquidity position and its impact on financially distressed firms in the industry as a whole, but most do not consider the impact of financial distress in an individual firm or company. Most of the published studies use statistical tools for the evaluation of financial distress. This study uses Multiple Discriminant financial model analysis. Multiple Discriminant financial model Analyses are very useful in deciding remedial actions for financial distress problems

Prediction and Comparison of Bankruptcy Models in Banking Sector Companies in Indonesia

The Covid-19 pandemic, coupled with the economic recession from 2019 to 2022, has adversely impacted various industries, leading to bankruptcies. Among the affected sectors, the banking industry faced significant challenges, experiencing disruptions in credit processes and fund distribution due to diminished purchasing power. This situation poses a severe threat to the banking sector, necessitating the monitoring of financial conditions through bankruptcy analysis as an early warning system for company performance. This study investigates potential differences in the results of financial distress prediction models—Altman, Springate, Zmijewski, Grover, and Ohlson—during the abnormal conditions of the Covid-19 pandemic. Using purposive sampling of banking companies listed on the IDX from 2019 to 2022, the study divided the samples into financial distress and non-financial distress categories. Analysis involved tests for multicollinearity assumptions, logistic regression, and accuracy/error rate calculations. The findings reveal variations in the predictive abilities of the Altman, Springate, Zmijewski, Grover, and Ohlson models. The Grover model emerged as the most accurate, with a 60% accuracy rate in predicting bankruptcy, while Altman, Springate, and Zmijewski models demonstrated low predictive values (0%, 0%, and 15% accuracy, respectively). The simplicity of the Grover model's measurement indicators, incorporating capital adequacy, EBIT, and ROA, offers a comprehensive view of bankruptcy prediction ratios. Moreover, stringent internal risk analysis and external factors, such as regulatory interventions, contribute to keeping banks resilient amid global economic crises. The research suggests that banking companies can benefit from employing the Grover method for bankruptcy analysis as part of their future anticipation strategy.

Automated Machine Learning in Bankruptcy Prediction of Manufacturing Companies

Industry 4.0 uses artificial intelligence and machine learning algorithms to optimize processes. The main goal of the manuscript is to analyze the possibilities of applying automated machine learning to predict company bankruptcy. The data sample consists of financial data of 9,771 manufacturing companies for the years 2020 and 2021 collected from the Finstat database. Two methods of automated machine learning, AutoML and H2O, were tested. The results were compared with five other methods - linear discriminant analysis, logistic regression, naive Bayes classifier, CatBoost and XGBoost. The resulting model was cross-validated through the 10-fold approach. The best results were achieved by H2O automated machine learning algorithm with an AUC of 90.13%, followed by the gradient boosting methods CatBoost with AUC of 90.05% and XGBoost (AUC of 88.61%) and another automated learning algorithm AutoML with AUC of 81.17%. The findings of this paper indicate possibilities to apply automated machine learning methods in predicting bankruptcy. However, it is necessary to distinguish between individual automated machine learning algorithms since they provide a different range of results.

Research on Corporate Bankruptcy Prediction Combining Financial Data and Algorithmic Models Based on the Impact of Deleveraging

Research on Corporate Bankruptcy Prediction Combining Financial Data and Algorithmic Models Based on the Impact of Deleveraging

Ensemble Classifiers for Bankruptcy Prediction Using SMOTE and RFECV

Ensemble Classifiers for Bankruptcy Prediction Using SMOTE and RFECV

A New Discrete Learning-Based Logistic Regression Classifier for Bankruptcy Prediction

A New Discrete Learning-Based Logistic Regression Classifier for Bankruptcy Prediction

Natural Language Processing and Deep Learning for Bankruptcy Prediction: An End-to-End Architecture

Natural Language Processing and Deep Learning for Bankruptcy Prediction: An End-to-End Architecture

Two-Step Classification for Solving Data Imbalance and Anomalies in an Altman Z-Score-based Bankruptcy Prediction Model

Two-Step Classification for Solving Data Imbalance and Anomalies in an Altman Z-Score-based Bankruptcy Prediction Model

A Bibliometric Analysis of Corporate Bankruptcy Prediction Research: Trends and Insights

A Bibliometric Analysis of Corporate Bankruptcy Prediction Research: Trends and Insights