Financial Distress Prediction Model Research Articles

A proposed multidimensional model for predicting financial distress: an empirical study on Egyptian listed firms

Although there has been a growing interest by researchers worldwide over the past decades to identify the factors pertaining to corporate financial distress and to develop financial distress prediction models that serve as early warning signs to the various firm stakeholders, notably to date, studies that were conducted were context specific and cannot be objectively generalized to other countries and rendered mixed inconclusive results. Therefore, the main objective of this study is to thoroughly investigate the factors that affect corporate financial distress in Egypt and to develop a multidimensional financial distress prediction model. Using comprehensive data of EGX100 listed firms, the researcher examines the role played by financial ratios, market-based indicators, macroeconomic factors, and corporate governance mechanisms in modeling corporate financial distress. Empirical results indicate that after controlling for the COVID-19 effects, the most significant financial ratios in predicting corporate financial distress are the working capital to total assets ratio, earnings before interest and taxes to total assets ratio, and the sales to total assets ratio. Such ratios are negatively related to the likelihood of corporate financial distress. However, the market value of equity to total liabilities ratio, and GDP growth rate have a positive impact on the likelihood of financial distress. However, the retained earnings to total assets ratio, the corporate governance mechanisms, the firm market capitalization, the interest rate, and the consumer price index are insignificant in predicting corporate financial distress in the Egyptian context. The resulting model demonstrates outstanding classification accuracy at around 96%.

Using machine learning techniques to assess the financial impact of the COVID-19 pandemic on the global aviation industry

Prediction of financial distress is a crucial concern for decision-makers, especially in industries prone to external shocks, such as the aviation sector. This study employs machine learning techniques on a comprehensive global dataset of aviation companies to develop highly accurate financial distress prediction models. These models empower stakeholders with informed decision-making capabilities to navigate the aviation industry's challenges, most notably exemplified by the COVID-19 pandemic. The aviation industry holds substantial economic importance, contributing significantly to revenue, employment, and economic activity worldwide. However, its susceptibility to external factors underscores the need for robust predictive tools. Leveraging advances in machine learning, this study pioneers the application of data-driven, non-parametric solutions to the aviation sector, both before and after the pandemic. Importantly, this study addresses a gap in the field by conducting comparative evaluations of prediction models, which have been lacking in previous research efforts, often leading to inconclusive outcomes. Key findings of the study highlight the Random Forest and Stochastic Gradient Boosting models as the most accurate in forecasting financial distress within the aviation industry. Notably, the study identifies debt-to-equity, return on invested capital, and debt ratio as the most important predictors of financial distress in this context.

Evaluating the efficacy of financial distress prediction models in Malaysian public listed companies

This research critically examines the precision of financial distress prediction models, with a particular focus on their applicability to Malaysian publicly listed companies under Practice Note 17 (PN17) from 2017 to 2021. Financial distress, defined as the imminent risk of bankruptcy evidenced by an inability to satisfy creditor demands, presents a significant challenge in corporate finance management. The study underscores the necessity of an efficient prediction model to strategize preemptive measures against financial crises. Unlike prior research, which predominantly compared prediction models without assessing their accuracy, this study incorporates an accuracy analysis to discern the most effective model. Utilizing the Grover and Zmijerski models, it assesses whether companies listed under PN17 are experiencing financial distress. A noteworthy finding is the substantial correlation between the return on assets (ROA) and the prediction of financial distress in these companies. Furthermore, the Grover model demonstrates a remarkable 100% accuracy rate, indicating its exceptional efficiency in forecasting financial distress. This research not only contributes to the existing body of knowledge on financial distress prediction but also offers practical insights for companies and stakeholders in the Malaysian financial market.

Accuracy Analysis of Financial Distress Prediction Models for Companies on the IDX Watchlist Board in 2020-2022 Period

Abstrak: Tujuan penelitian adalah menguji tingkat keakuratan model prediksi financial distress Altman, Grover, Zmijewski, dan Springate, menggunakan data keuangan perusahaan yang masuk kriteria 5 atau 8 di Papan Pemantauan Khusus BEI pada periode 2020- 2022. Penelitian ini menggunakan metode kuantitatif dengan teknis analisis deskriptif. Pengujian data menggunakan uji Kruskal Wallis One Way Anova karena terdapat lebih dari dua model prediksi yang dibandingkan, kemudian data tidak berdistribusi normal. Sebanyak 44 sampel yang dipilih menggunakan teknik puposive diambil dari 55 populasi emiten yang masuk dalam Papan Pemantauan Khusus BEI. Hasil penelitian menunjukkan bahwa tidak terdapat perbedaan yang signifikan antara akurasi model Altman, Grover, Zmijewski, dan Springate. Ditunjukkan dari hasil akurasi berdasarkan jumlah prediksi benar dari masing-masing model, Zmijewski merupakan model paling akurat dengan tingkat akurasi 67%, disusul Altman 65%, Grover 65%, dan terendah Springate 60%
 
 Abstract: The research aims to examine the accuracy level of the Altman, Grover, Zmijewski, and Springate financial distress prediction models, to determine the most accurate financial distress prediction model in analyzing companies on the IDX Watchlist Board criteria 5 or 8 between 2020 and 2022. This study employs a quantitative method with descriptive analytical techniques. Data testing utilizes the Kruskal-Wallis One-Way ANOVA test due to the comparison of more than two prediction models and the non-normal distribution of the data. A total of 44 samples, purposively selected from the population of 55 listed issuers within the DPK-BEI, were used. The research findings reveal no significant differences in the accuracy among the Altman, Grover, Zmijewski, and Springate models. This is evidenced by the accuracy results based on the number of correct predictions from each model. Zmijewski emerges as the most accurate model with a 67% accuracy rate, followed by Altman and Grover at 65% each, and Springate with the lowest accuracy at 60%.

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.

Analisis Financial Distress pada Perusahaan Konstruksi BUMN Karya

This study aims to measure the performance and financial health of the BUMN Karya Construction Company based on an analysis of financial reports from 2019 to 2022. This research is also intended to determine increases or decreases in financial performance and even financial distress. This study examines financial problems in 5 (five) BUMN Karya companies, including PT. Adhi Karya, PT. Waskita Karya, PT. Wijaya Karya, PT. Pembangunan Perumahan and PT. Hutama Karya. Financial performance measurement analysis based on Financial Ratio Analysis and Discriminant or Financial Distress Prediction Models include the Altman Z-score Model, the Springate Model, the Grover Model and the Zmijewski Model. The research will be measured based on the individual analysis of each company and the comparative analysis of the 5 (five) BUMN Karya. The results of the research based on analysis of financial ratios and 4 (four) financial distress models obtained values of 50% to 100%, so that it can be concluded that 5 (five) BUMN Karya companies are experiencing financial distress or financial difficulties and are on the verge of bankruptcy. While the research results are based on the calculation of financial ratios where the average state-owned company works, the majority of its assets come from debt but still have sufficient cash to pay off its debts. The conclusion from the results of this study can be used as an early warning related to the company's financial condition, so that it can be planned to develop company policies and strategies for better financial performance and avoid financial distress.

Analisis Perbandingan Prediksi Financial Distress menggunakan Model Altman, Grover, Ohlson, Springate dan Zmijewski: Studi Empiris pada Perusahaan Sub Industri Perkebunan dan Tanaman Pangan yang terdaftar di Bursa Efek Indonesia Periode Tahun 2017-2021

The aim of this research is to find out which financial distress prediction model is most suitable for plantation and food crop sub-industry companies in Indonesia. This study compares five financial distress prediction models, namely the Altman, Grover, Ohlson, Springate, and Zmijewski models by analyzing the level of accuracy of each model. The research data was taken from the financial statements of plantation and food crop sub- industry companies listed on the Indonesia Stock Exchange (IDX) for the 2017-2021 period. The samples used in this study were 15 companies using a purposive sampling technique. The analytical method used in this study is logistic regression. The results of the study show that the Altman, Grover, and Springate models can be used to predict financial distress in plantation and food crop sub-industry companies in Indonesia. The model with the best level of accuracy is the Springate model

Financial distress prediction in private firms: developing a model for troubled debt restructuring

Purpose This study aims to develop a model based on the financial variables for better accuracy of financial distress prediction on the sample of private French, Spanish and Italian firms. Thus, firms in financial difficulties could timely request for troubled debt restructuring (TDR) to continue business.Design/methodology/approach This study used a sample of 312 distressed and 312 non-distressed firms. It includes 60 French, 21 Spanish and 231 Italian firms in both distressed and non-distressed groups. The data are extracted from the ORBIS database. First, the authors develop a new model by replacing a ratio in the original Z”-Score model specifically for financial distress prediction and estimate its coefficients based on linear discriminant analysis (LDA). Second, using the modified Z”-Score model, the authors develop a firm TDR probability index for distressed and non-distressed firms based on the logistic regression model.Findings The new model (modified Z”-Score), specifically for financial distress prediction, represents higher prediction accuracy. Moreover, the firm TDR probability index accurately depicts the probabilities trend for both groups of distressed and non-distressed firms.Research limitations/implications The findings of this study are conclusive. However, the sample size is small. Therefore, further studies could extend the application of the prediction model developed in this study to all the EU countries.Practical implications This study has important practical implications. This study responds to the EU directive call by developing the financial distress prediction model to allow debtors to do timely debt restructuring and thus continue their businesses. Therefore, this study could be useful for practitioners and firm stakeholders, such as banks and other creditors, and investors.Originality/value This study significantly contributes to the literature in several ways. First, this study develops a model for predicting financial distress based on the argument that corporate bankruptcy and financial distress are distinct events. However, the original Z”-Score model is intended for failure prediction. Moreover, the recent literature suggests modifying and extending the prediction models. Second, the new model is tested using a sample of firms from three countries that share similarities in their TDR laws.

THE EFFECT ANALYSIS OF EARNING MANAGEMENT AND FAMILY CONTROL ON THE Z-SCORE MODEL OF FINANCIAL DISTRESS PREDICTION

The validity of the use of financial statements as a source of information for detecting financial distress is questionable because of the opportunistic behaviour of the company’s management. This study aims to analyse the effect of accrual earnings management, real earnings management, and family control on the Z-score financial distress prediction. Using the sample that includes 372 firm years of observations for the 2017 to 2019 periods listed on the Indonesia Stock Exchange, this study found that accrual earnings management, real earnings management, and family control variables affect the Z-score financial distress prediction and cause a higher probability for the company to be in the category of better financial condition. The novelty of this study lies in earnings management and family control as factors that affect the category of assessment and the probability of assessing the company’s financial condition as a better company. Empirical evidence from this study is important for investors and company creditors, as input to consider these factors in using the company’s financial distress prediction model. For standard setters, the results of this study can be used as input for establishing corporate governance design rules to improve the quality of financial information.

Analisis Ketepatan Model Prediksi Financial Distress pada Perusahaan Sektor Properti dan Real Estate

The study aims to analyze differences in the accuracy of the financial distress prediction model using Altman Z-Score , Zmijewski, Springate, and Grover for property and real estate sector companies listed on the Indonesia Stock Exchange in 2021. The sampling method uses non- probability sampling with a purposive sampling method. The number of samples used in this study were 63 companes. The data analysis method used is to test the accuracy of the prediction model and the chi square test. The result of this study indicated that there are differences in the accuracy of financial distress predictions using four models, Altman Z-Score, Zmijewski, Springate, and Grover for property and real estate sector companies listed on the Indonesia Stock Exchange.

The role of feature importance in predicting corporate financial distress in pre and post COVID periods: Evidence from China

The prediction of firm financial distress during the COVID-19 crisis episode attracted massive academic attention since economic uncertainty was exacerbated. In this paper, we propose a firm financial distress prediction model based on the Extreme Gradient Boosting-Genetic Programming (XGB-GP) framework by investigating subsamples of pre-COVID and post-COVID periods. The key contribution of our paper is that we explore time-varying prediction features for pre-COVID and post-COVID periods. We illuminate that the earning financial indicator is the dominant feature for financial distress prediction during the pre-COVID period, whereas total financial leverage is the most important factor during the post-COVID period. On this basis, our XGB-GP financial distress prediction model exhibits higher prediction accuracy than the traditional models. As a result, managers can modify the financial leverage level to improve the financial situation of the firm by reducing the debt burden and increasing profitability during the post-COVID period.

Financial distress prediction using the Q&A text of online interactive platforms

The text-based question and answer (Q&A) information of online interactive platforms reflects the concerns of investors and the responses of companies, which can reduce information asymmetry and risk accumulation. This paper proposes a framework to predict the financial distress of companies and explores whether the features extracted from Q&A text can significantly improve the performance of financial distress prediction (FDP) models. In this framework, we extract interactive features, a question sentiment feature, an answer satisfaction feature and topic features. Experimental results show that interactive features and topic features can significantly improve the performance of FDP models compared with the model using only financial features. In addition, we apply the Shapley value method to identify the key factors in predicting the financial distress of companies, providing a basis for investors and managers to make decisions.

CHOOSING RATIO IN THE FINANCIAL DISTRESS PREDICTION MODEL

Purpose – This study aims to find a financial distress prediction model that is suitable for Indonesian companies.Design/methodology/approach – The sample in this study amounted to 150 data. The research sample was grouped into financial distress and non-financial distress. Research data is sourced from the Indonesia Stock Exchange. Discriminant analysis is used to test data and generate financial distress prediction models for manufacturing companies in Indonesia.Findings – Results show that the financial ratios that contribute to the financial distress prediction model are the ratios of profitability, liquidity, and efficiency.Practical Implications – The resulting model can contribute and as a basis for the development of future studies on relevant, robust, and accurate corporate financial distress early warning systems that will help stakeholders to respond to potential bankruptcies accordingly and on timeOriginality – Research on new models to predict corporate bankruptcy in Indonesia which is a developing country is still rare. Most of the literature still uses the Altman Z-Score model.

Determinants of potential bankruptcy of companies during the Covid-19 pandemic

<p>The Covid-19 pandemic has had a real and widespread impact on all industries in Indonesia, potentially increasing corporate bankruptcy (financial distress). This study examines the effect of financial ratios on financial distress in various industrial sub-sectors on the Indonesia Stock Exchange during and before the pandemic. The research began with creating a financial distress prediction model using the Logistics Regression Model with monetary and macroeconomic ratio data input during 2016 – 2020. The economic distress prediction model will measure financial distress during the Pandemic and Pre-Pandemic Periods. Empirical testing shows that the pandemic affects the ability of financial ratios to predict bankruptcy. Only the debt ratio and sales growth were significant in predicting bankruptcy during the pre-pandemic period, but cash flow could also expect a default during the pandemic. During a pandemic, sales growth is the most important because it is the aspect most affected by restrictions on consumers' social and economic activities.</p>

GALSTM-FDP: A Time-Series Modeling Approach Using Hybrid GA and LSTM for Financial Distress Prediction

Despite the obvious benefits and growing popularity of Machine Learning (ML) technology, there are still concerns regarding its ability to provide Financial Distress Prediction (FDP). An accurate FDP model is required to avoid financial risk at the lowest possible cost. However, in the Internet era, financial data are exploding, and they are being coupled with other kinds of risk data, making an FDP model challenging to operate. As a result, researchers presented several novel FDP models based on ML and Deep Learning. Time series data is are important to reflect the multi-source and heterogeneous aspects of financial data. This paper gives insight into building a time-series model and forecasting distress far in advance of its occurrence. To build an efficient FDP model, we provide a hybrid model (GALSTM-FDP) that incorporates LSTM and GA. Unlike other previous studies, which established models that predicted distress probability only within one year, our approach predicts distress two years ahead. This research integrates GA with LSTM to find the optimum hyperparameter configuration for LSTM. Using GA, we focus on optimizing architectural aspects for modeling the optimal network based on prediction accuracy. The results showed that our algorithm outperforms other state-of-the-art methods in terms of predictive accuracy.

Pengaruh Curent Ratio dan Total Assets Turnover Terhadap Financial Distress Pada Sektor Transportasi dan Logistik yang Terdaftar di BEI 2017-2021

Financial distress can be interpreted as a decrease in the company’s financial condition before bankrupty. As a financial distress prediction model, this study aims to determine the effect of Liquidity (Curent Ratio) And Activity (Total Assets Turnover) on Financial Distress in the transportation and logistics sector listed on the Indonesia Stock Exchange (IDX). The research time period used is 5 years, namely the 2017-2021 period. The research method to be used in the study is Panel Data Regression Analysis use the Eviews program with a significance level of 5% . The results of this study shows that Liquidity (Curent Ratio) has no effect on Financial Distress, while Activity (Total Assets Turnover) has a negative effect on Financial Distress. But simultaneously, Liquidity (Curent Ratio) and Activity (Total Assets Turnover) have an effect on Financial Distress. This research indicates that that liquidity (current ratio) is not a factor that affects financial distress while activity (total assets turnover) is a factor that affects financial distress.Keywords : Activity; Curent Ratio; Financial Distress; Liquidity; Total Assets Turnover

May board committees reduce the probability of financial distress? A survival analysis on Italian listed companies

The aim of this research was to study the effect of the composition and functioning of board committees on firms' financial distress. Exponential, Weibull and Cox regression models were used to conduct a survival analysis on a sample of 273 Italian listed companies for the period 2004–2017, which indicated that the presence of non-executive members on remuneration and audit committees, and remuneration committees meeting more frequently may enhance firms' stability. In contrast, a high frequency of nomination committee meetings seems to be positively related to the probability of financial distress.Although we only partially controlled for endogeneity issues, our findings contribute to the literature on financial distress-prediction models by deepening the importance of the composition and functioning of board committees (beyond other corporate governance variables and financial ratios). We can also provide firms with practical suggestions to promote financial stability.

Dynamic class-imbalanced financial distress prediction based on case-based reasoning integrated with time weighting and resampling

Existing dynamic class-imbalanced financial distress prediction (FDP) models based on artificial intelligence, such as support vector machines or neural networks, are difficult to understand. Case-based reasoning (CBR) is an artificial intelligence method that is easy for users to understand, but traditional FDP models based on CBR lack mechanisms for treating concept drift and class imbalance. This study explores the construction of a dynamic class-imbalanced CBR FDP model, which consists of four modules (dynamic updates of the case base, class balancing of the case base by resampling, the time weighting of cases and CBR for FDP). It treats financial distress concept drift by dynamically updating the case base and via a time-weighting mechanism, and solves the class imbalance problem by resampling. Empirical experiments based on real-world data from Chinese listed companies show that the proposed dynamic class-imbalanced CBR FDP model outperforms both static and dynamic CBR FDP models without resampling or time weighting. Therefore, the dynamic class-imbalanced CBR FDP model not only gives a satisfying performance by effectively treating the problems of both financial distress concept drift and class imbalance but also has good interpretability in real-world applications, providing corporate managers and other stakeholders with a new risk management tool.

Employing Artificial Neural Networks and Multiple Discriminant Analysis to Evaluate the Impact of the COVID-19 Pandemic on the Financial Status of Jordanian Companies

Aim/Purpose: This paper aims to empirically quantify the financial distress caused by the COVID-19 pandemic on companies listed on Amman Stock Exchange (ASE). The paper also aims to identify the most important predictors of financial distress pre- and mid-pandemic. Background: The COVID-19 pandemic has had a huge toll, not only on human lives but also on many businesses. This provided the impetus to assess the impact of the pandemic on the financial status of Jordanian companies. Methodology: The initial sample comprised 165 companies, which was cleansed and reduced to 84 companies as per data availability. Financial data pertaining to the 84 companies were collected over a two-year period, 2019 and 2020, to empirically quantify the impact of the pandemic on companies in the dataset. Two approaches were employed. The first approach involved using Multiple Discriminant Analysis (MDA) based on Altman’s (1968) model to obtain the Z-score of each company over the investigation period. The second approach involved developing models using Artificial Neural Networks (ANNs) with 15 standard financial ratios to find out the most important variables in predicting financial distress and create an accurate Financial Distress Prediction (FDP) model. Contribution: This research contributes by providing a better understanding of how financial distress predictors perform during dynamic and risky times. The research confirmed that in spite of the negative impact of COVID-19 on the financial health of companies, the main predictors of financial distress remained relatively steadfast. This indicates that standard financial distress predictors can be regarded as being impervious to extraneous financial and/or health calamities. Findings: Results using MDA indicated that more than 63% of companies in the dataset have a lower Z-score in 2020 when compared to 2019. There was also an 8% increase in distressed companies in 2020, and around 6% of companies came to be no longer healthy. As for the models built using ANNs, results show that the most important variable in predicting financial distress is the Return on Capital. The predictive accuracy for the 2019 and 2020 models measured using the area under the Receiver Operating Characteristic (ROC) graph was 87.5% and 97.6%, respectively. Recommendations for Practitioners: Decision makers and top management are encouraged to focus on the identified highly liquid ratios to make thoughtful decisions and initiate preemptive actions to avoid organizational failure. Recommendation for Researchers: This research can be considered a stepping stone to investigating the impact of COVID-19 on the financial status of companies. Researchers are recommended to replicate the methods used in this research across various business sectors to understand the financial dynamics of companies during uncertain times. Impact on Society: Stakeholders in Jordanian-listed companies should concentrate on the list of most important predictors of financial distress as presented in this study. Future Research: Future research may focus on expanding the scope of this study by including other geographical locations to check for the generalisability of the results. Future research may also include post-COVID-19 data to check for changes in results.

A deep learning approach of financial distress recognition combining text

<abstract><p>The financial distress of listed companies not only harms the interests of internal managers and employees but also brings considerable risks to external investors and other stakeholders. Therefore, it is crucial to construct an efficient financial distress prediction model. However, most existing studies use financial indicators or text features without contextual information to predict financial distress and fail to extract critical details disclosed in Chinese long texts for research. This research introduces an attention mechanism into the deep learning text classification model to deal with the classification of Chinese long text sequences. We combine the financial data and management discussion and analysis Chinese text data in the annual reports of 1642 listed companies in China from 2017 to 2020 in the model and compare the effects of the data on different models. The empirical results show that the performance of deep learning models in financial distress prediction overcomes traditional machine learning models. The addition of the attention mechanism improved the effectiveness of the deep learning model in financial distress prediction. Among the models constructed in this study, the Bi-LSTM+Attention model achieves the best performance in financial distress prediction.</p></abstract>