See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/364652575

THE ANALYSIS OF ALTMAN AND OHLSON MODEL IN PREDICTING DISTRESS OF

INDIAN COMPANIES: A REVIEW

Article  in  Solid State Technology · December 2020

CITATIONS READS

0 26

7 authors, including:

Rohit Bansal
Lovely Professional University
18 PUBLICATIONS   20 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Framing financial distress prediction model for Indian companies View project

All content following this page was uploaded by Rohit Bansal on 23 October 2022.

The user has requested enhancement of the downloaded file.

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

THE ANALYSIS OF ALTMAN AND OHLSON MODEL

IN PREDICTING DISTRESS OF INDIAN COMPANIES:
A REVIEW
Rohit Bansal
Assistant Professor, Mittal School of Business, Lovely Professional University, India
Nittala S V N Sai Pavan Raghava Pranav , Ummidi Siva Krishna , Zeeshan Ahmad and
Anjali Chauhan
MBA Student, Mittal School of Business, Lovely Professional University, India

Abstract - Bankruptcy is that state of insolvency in which a company or an organization cannot discharge their financial
obligation or are unable to meet the payments to their creditor. These bankruptcy prediction models include different
financial ratios as independent variables and are developed using different econometric methods: multiple discriminant
analysis, logistic regression, and probit regression, respectively. It is tested if one of the prediction models outperforms
the others, which econometric method is best for developing the models, if the coefficients of the models are non-
stationary, and what the optimal time horizon for predicting bankruptcy is. With time, however, advanced methods began
to be introduced and new models included non-financial variables. Also, research on the selection of the samples was
conducted.
Keywords: Bankruptcy Prediction, Discriminant Analysis, Financial ratios, Variables, Regression

INTRODUCTION
Almost more than 70 years, business failure has been one of the most discussing topics in the financial literature Cultrera
and Brédart(2016).One should carefully selected business partners to survey in the financial market. One aspect of risk
management is to observe the operations of companies and predict the financial distress of the companies. Risk related to
the financial problems of the companies is not only taken by customers, suppliers, and creditors but also investors and
speculators. Recognition of financial distress in the affiliated company reduces the risk of potential losses Begović et al
(2020). Where most of the organizations exist with an objective of profit maximization. To achieve a profit maximization
objective, the firm needs strong internal and external support. The failure of an internal support system such as effective
utilization of funds, labor, material, etc and external support system such as economic, political, and socio-cultural
conditions results in the bankruptcy of the organization Joshi(2019). Predicting failure is one of the most challenging
topics in the financial field, especially in recent years. It is the ability to predict if a company will fall into bankruptcy or
not. It is an essential key point for decision-making in many cases, particularly in the areas of investment and lending.
Setting up an early prediction of business failures based on their financial behavior is significantly improve decision-
making Azayite and Achchab (2019). Decision-making has various techniques, hypothetical models, mathematical
techniques, and soft computing techniques to predict and estimate the rate of bankruptcy overtime on financial ratios.
Predictions can be done based on single- multivariable models and hypothetical models, are implemented to support
theoretical principles but they are statistically complex, and development is done based on assumptions. These limitations
can be reduced by including soft computing techniques such as Bayesian networks, decision trees, logistic regression and
SVM in the design process. Further, failures occurring in business sectors and credit and contract can be detected using
bankruptcy prediction models (Devi and Radhika (2019)). Many techniques are implemented and developed by different
authors. Previous study by Adamko and Chutka (2020) examined in an economic environment business constantly
evolving and changing, depending on many different factors. Economic space has given businesses a huge market,
covering almost the whole of Europe, with many business opportunities but also competitors. Prior research by
Agyirakwah and Musah (2019) examined there is a relationship between corporate governance characteristics and
corporate failure. Almost every major economy in the world has its fair share of corporate failures of which Ghana is not
an exception. In context to develops as well as developing economies. Initial analysis by Bouwmeester (2020) examined
1

corporate bankruptcy prediction is of great interest to various stakeholders. Predicting the possibility of bankruptcy can
help investors evaluate and select firms to invest in, to prevent the risk of losing their investment and an early warning

Archives Available @ www.solidstatetechnology.us

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

system to prevent bankruptcy. Previous survey by Prusak( 2019) examined financial indicators and figures are used in the
area of corporate governance. Ratio analysis can be used to assess the risk of insolvency and discriminant analysis to
predict the risk of enterprise bankruptcy. Earlier research by Tian and Hartling (2019) examined the possibility of
linking greenhouse gas emission to negative financial performance expressed as corporate bankruptcy. The result
suggested the risk of being default will be considerably lower comparing to others in a long run . Previous study by Affes
and Kaffel (2016) examined the contagion of bank failures is to assess the bank failure rate. The approach helps to
establish an early warning model of bank difficulties. Earlier research by Kubickova and Nulicek (2019) examined
prediction of future development and early identification of possible failure in the future is very important and usable
information for all stakeholders by the reliability of predictions of individual models. Previous analysis by Song and
Peng (2019) examined to rank imbalanced classifiers in credit and bankruptcy risk prediction according to their
performances on a selection of metrics, rather than singular metric using MCDM methods. Previous research by Khan
and Raj (2019) examined the impact of liquidity on profitability and analyze the overall financial health of the Indian
Telecom industry. Financial management experts have devised many techniques to predict the financial health of a
company and bankruptcy. Earlier analysis by Aalbers (2019) examined distressed firms that are enabled to restructure and
adapt to changing environments through a bankruptcy proceeding, while at the same time limiting bankruptcy costs and
public scrutiny . Early study by Khaerunnisa and Rahayu (2019) examined the company’s deficit or didn't have enough
money to run its business. To avoid bankruptcy, the company could able to perform a bankruptcy prediction. Previous
research by Csikosova et al (2019) examined the forecast of financial issues of the organization, different lists are
utilized which will work a contribution for master assessment or making of fluctuated models (Horak et al (2020))
studied Bankruptcy prediction is usually a topical issue. In financial bankruptcy examination, the distinguishing proof of
organizations in danger of insolvency is pivotal in getting ready to shield against any monetary harm the in danger firms
remain to dispense. the most problem is relating the subsequent measurable strategies to corporate insolvency assurance
The dichotomous variable , The testing technique, Non fixed and information precariousness, the usage of yearly record
data, the decision of the autonomous factors. Previous studies by (Ogachi et al(2020)) examined foreseeing liquidation of
organizations has been a hot subject of center for a few financial experts. Insolvency expectation might be a procedure of
estimating and anticipating on organization monetary trouble of both public and firms. the point of foreseeing liquidation
is prime in evaluating the monetary state of a partnership and possibilities in its activities. However, two significant
problems related to this approach include the problem to form consistent estimates and therefore the incontrovertible fact
that it tends to be reactive instead of predictive. Previous analysis by (Karas and Režňáková (2020)) examined
bankruptcy prediction models supported the tactic of linear discriminant analysis represent a widely used tool for
analyzing corporate failures or evaluating a company’s financial health. However, the problem concerning bankruptcy
prediction models is whether or not these models are often effectively applied to different economic environments or time
periods from that during which the training data were observed. Prior study by(Singh and Mishra (2019)) analyzed
Previous studies on bankruptcy prediction focused on recognizing huge pointers to anticipate insolvency. the overall
Financial Crisis of 2008 made credit hazard inevitable and Basel III concurring was the consistent worldwide reaction to
manage the matter of credit hazard. Early research by (Bateni and Asghari. (2020)) examined one of the primary
reasonable investigations of liquidation hypothesis, insolvency is thought about a situation during which an organization's
all out revenue expenses of long haul liabilities are very its incomes. steady with the premier regular exhibitions, a
populace of applicant arrangements is kept up, and after an age is cultivated, the populace is anticipated fitted better for a
given issue. previous survey by (Inam et al (2019)) studied Organizational sustainability are often achieved by giving
importance to economic, social, and environmental aspects. Considering the economic aspects of an organization ,
different financial difficulties may lead toward bankruptcy. A firm may face multiple consequences when it's exposed to
financial issues like bankruptcy or liquidation and fail to figure as a going concern. Financing problems and operating
problems are the tow key issues that are related to a going concern that stakeholders consider by observing the financial
statements. Earlier research by (MuñozIzquierdo et al (2019)) analyzedthe most recent 70 years, the occasion of
liquidation forecast models has been a difficult exploration point around the world. In spite of the measure of studies
during this field, late writing shows there's as yet a necessity to fortify the exactness of the forecast models and there is a
call to utilize various wellsprings of information and methods, as non-parametric procedures, to handle this issue. This
paper aimed to contribute to the present line of research by examining the bankruptcy predictive ability of the external
audit report using AI methodologies. Previous research by (Ouenniche et al (2019)) studied that the financial industry is
2

amongst those industries where predictive analytics techniques are widely wont to predict both continuous and discrete
variables. Conceptually, the prediction of discrete variables comes right down to addressing sorting problems,

Archives Available @ www.solidstatetechnology.us

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

classification problems, or clustering problems. the main target of this paper is on classification problems as they're the
foremost relevant in risk-class prediction within the financial industry
LITERATURE REVIEW
Ouenniche et al (2019) examined predictive analytics techniques for risk-class prediction by collecting data of VIKOR-
based classifier and CBR based classifier. The result showed that classifiers can deliver predictive performance in the
industry of applications in finance and investment. Adamko and Chutka (2020) examined a new range of methods on
how to analyze optimize and minimize risks in global markets by multidimensional models assessing the overall financial
situation of a company by providing a single result value. The result indicated a sufficient degree of probability for the
future development of the company in advance. Musah and Agyirakwah (2019) examined the appropriateness of the
Altman Z-score model in anticipating bankrupt organizations or monetarily troubled organizations on the Ghana securities
exchange by choosing 10 recorded firms of the 2017 budget summary utilizing the bookkeeping proportions scoring
model in a univariate discriminant investigation to foresee the danger of bankruptcy of organizations. The outcome drawn
demonstrated that Altman Z-score can't precisely anticipate monetarily upset firms in Ghana yet can at present be helpful
in giving signs. Bouwmeester (2020) examined the prediction power of the accounting-based bankruptcy prediction
models and large private firms by using multiple discriminant analysis, logistic regression, and probit regression by taking
data from 2010 to 2019. The result showed that reduction of risk, banks need to predict the possibility of default risk of a
potential borrower. Prusak (2019) examined to present and evaluate the scientific achievements of in the field of
corporate bankruptcy prediction and compare them to global trends by using simple tools to assess the risk of bankruptcy
of enterprises. The result showed institution of bankruptcy in practice remained a dead letter in the postwar period until
1990 and many attempts were made to implement foreign solutions in national conditions and to use ratio analysis.Tian
and Hartling (2019) examined the linkage between the Greenhouse Gas (GHG) emission and the corporate default risk at
different prediction horizons through a bottom-up approach upon process analysis and top-down approach upon
environmental input-output analysis. The result showed investment in being green might present some financial hurdles in
a short term. But in a long run, companies with better environmental performance demonstrate lower default risk. Affes
and Kaffel (2016) examined an early warning framework to identify banks leading to bankruptcy by comparative analysis
based on both Canonical Discriminant Analysis and Logistic models to examine and determine the most accurate of these
models. The result indicated that the combination of the two models allows better information about the future prospect of
banks. Kubickova and Nulicek (2019) examined to construct new versions of the older models as well as the new models
based on the wider scale of variables by selecting a set of 80 Czech companies operating in the Czech market of the year
2017. The result indicated greater reliability of the model in national conditions has been identified as the one created in
terms of another transition economy. Song and Peng (2019) examined a multi-standards choosing (MCDM)- based way
to deal with guage imbalanced classifiers in credit and liquidation hazard expectation by considering various execution
measurements at the same time to supply an exhaustive assessment of imbalanced classifiers. The result indicated that
default and bankruptcy are rare events compared to normal accounts and companies functioning well, which indicates that
financial risk data are imbalanced by nature. Khan and Raj (2019) examined analyzing the financial health of the Indian
Telecom Industry and predicting the bankruptcy of selected companies. There are around ten telecom companies in Indian
Telecom Industry, the top six companies were selected for the study based on market capitalization. The result indicated
that most of the telecom companies in the Indian Telecom Industry fall in the
“Grey” zone of the Altman Z-score model, which is not a good sign for the Industry and the study also found out that
most of the companies, did not perform well in terms of liquidity and profitability. Begović et al (2020) studied the
impact of the financial problem on the Serbian market by comparing two corporate bankruptcy prediction models, based
on accounting data. These are the models that have been widely applied in practice, i.e. Altman Z and Zmijewski
model, to determine which model applied to Serbian companies.The results of the survey showed that the accuracy of
predicting the bankruptcy of the Altman model for emerging markets on Serbian companies undergoing bankruptcy
proceedings.Azayite and Achchab (2019) studied the optimum Artificial Neural networks (ANN) to discriminate
between bankrupt and non-bankrupt firms to identify data with noisy, missing Data and firms’ health with high accuracy
of variables selection models by comparing Multivariate Discriminant Analysis, Logistic Regression, and Decision
Trees. The results showed high performance of Decision Trees as variables selection models for ANN to discriminate
between Bankrupt and non-bankrupt firms. Joshi(2019) studied the Early prediction of the company going for
3

bankruptcy is of prime importance to the stakeholders of the company and the society by analyzing the financial
statement and the market data of Reliance communication by using the Altman Z score model to analyze bankruptcy

Archives Available @ www.solidstatetechnology.us

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

prediction.The results showed that the model was good in predicting the upcoming financial distress of Reliance
communication which can lead towards Bankruptcy as their Z score was in the distress zone 3 years before they filed for
bankruptcy. Devi and Radhika (2019) examined effective prediction models to evaluate the risks arising in bankruptcy
at the early stages and to overcome financial losses and periodic increases in financial data and updates. by using a
combined approach of Big Data and Naive Bayes machine learning algorithm, to show a better classification rate with
higher accuracy being obtained compared with other existing techniques.The results showed a better classification rate
with higher accuracy being obtained compared with other existing techniques.Wang et al(2017) studied a new kernel
extreme learning machine (KELM) that is embraced to build a proficient KELM model for insolvency forecast by
contrasting and three serious KELM strategies, which are ordinary during an exhaustive arrangement of techniques
including molecule swarm advancement based KELM, hereditary calculation based KELM, matrix search method based
KELM, outrageous learning machine, improved extraordinary learning machine, uphold vector machines, and arbitrary
backwoods, on two genuine datasets by 10-crease crossapproval analysis.the results demonstrated that the prevalence of
the created model as far as order precision (preparing, approval, test), Type I blunder, Type II mistake, region under the
recipient working characterisic work (AUC) measure also as computational time and GWO-KELM prediction model is
promising to serve as a powerful early warning tool with excellent performance for bankruptcy prediction.Kovacova
and Kliestik(2017) studied important writing and utilization of reasonable picked numerical measurable strategies for
bankruptcy expectation of Slovak organizations and supply the correlation of the overall prescient capacity of the 2
created models by gathering the data of Slovak enterprises covering the year 2015 and two numerical factual techniques
was applied. The techniques are logit and probit, which are both symmetric parallel decision models, additionally alluded
to as unexpected likelihood models, zeroed in on the improvement insolvency forecast model in the Slovak Republic by
strategic relapse and probit model. The aftereffects of the investigation demonstrated recommend that the model upheld a
logit work marginally outflanks the arrangement exactness of the probit model and there's Differences are acquired
inside the most crucial indicators of chapter 11 in such models. Alaka et al (2018) examined guidelines for the choice of
tools which will be best fit different situations and better performance models for bankruptcy prediction by Utilizing the
online of Science, Business Source Complete, and Engineering Village information bases, and a logical audit of 49 diary
articles distributed somewhere in the range of 2010 and 2015. the outcomes demonstrated that 13 models recognized are
precision, result straightforwardness, completely deterministic yield, information size capacity, information scattering,
variable choice technique required, variable sorts pertinent, and more it had been discovered that no single instrument is
transcendently in a way that is better than different devices about the 13 distinguished measures for. Le et al(2018)
studied the machine learning model to compare the bankruptcy companies with non- bankruptcy companies and to
implement the bankruptcy prediction framework by used five oversampling techniques that deal with imbalance
problems on the experimental dataset which were collected from Korean companies in two years from 2016 to 2017.This
shows that using oversampling techniques to balance the dataset in the training stage can enhance the performance of the
bankruptcy prediction. Altman et al (2014) examined the viability and result of the Altman Z-Score chapter 11 forecast
model worldwide and its organizations in Finance and related regions. By investigating and dissecting of 34 logical
papers distributed from the year 2000 in driving monetary and bookkeeping diaries and they have utilized an enormous
global example of firms to evaluate the order execution of the model in liquidation and bothered firm expectation to
examine its presentation in firms from 32 European and three non-European countries.The analysis in this study shows
that the overall global model functions admirably for some nations, with forecast precision levels of about 75%, and
uncommonly well for a couple (above 90%), the characterization exactness could likewise be extensively improved with
nation explicit assessment. In some other nation models, the data gave by extra factors helps support the characterization
exactness to a more elevated level. Cultrera and Brédart (2016) investigated to build up a liquidation forecast model
for the Belgian little and Medium estimated undertakings (SMEs) through the structure of a logit model that includes
such a money related ratios.by utilizing an example of seven ,152 Belgian SMEs among which 3,576 are proclaimed as
bankrupt somewhere in the range of 2002 and 2012 and this model incorporates control factors like firm size and age,
which plans to check the prescient influence of proportions mirroring the monetary structure, benefit, dissolvability, and
thusly the liquidity of firms.The aftereffects of this investigation indicated that the expectation precision of the model
and show that proportions as productivity and liquidity are magnificent in indicators of bankruptcy for Belgian SMEs.
Horak et al (2020) examined the activities of all business entities are suffering from various factors which will affect a
corporation leads to bankruptcy by Collecting data from Support Vector Machine and artificial neural networks, and
TIBCO’s Statistical software, version 13, is used to evaluate the results of the methods used. The result of this study
4

showed that the most successful one applicable in practice is that the model determined by the structure 2.MLP 22-9-2.

Archives Available @ www.solidstatetechnology.us

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

This model of Support Vector Machine shows relatively high accuracy, but it's not applicable within the structure of
correct classifications. Ogachi et al(2020) studied and sought to introduce deep learning models for corporate
bankruptcy forecasting using textual disclosures by collecting data from an area (Grünberg’s) bankruptcy prediction
model. They were wont to calculate bankruptcy scores for the primary and second pre-bankruptcy years. The results
show that inventory turnover, asset turnover, debt-equity ratio, debtors turnover, total asset, debt ratio, current ratio, and
dealing capital ratio were the foremost significant ratios for predicting bankruptcy. Karas and Režňáková (2020)
analyzed Bankruptcy prediction models based on the method of linear discriminant analysis. The samples that are used
in companies and the manufacturing industry that is under investigation is comprised of the LDA method, the analyzed
model. The result of this study showed that the criterion that can be used for deriving a grey zone that on one hand
maximizes model accuracy, while on the other hand minimizes the number of unevaluated companies. Singh and
Mishra. (2019) studied that bankruptcy prediction focused on identifying significant indicators to predict bankruptcy by
studying the utilizes Multivariate Discriminant Analysis (MDA), logit and probit econometric procedures to show
insolvency, Secondary example, long-range precision, and Receiver Operating Characteristic (ROC) tests were utilized
for the approval of liquidation forecast models. The investigation recommended that the bookkeeping information's,
specifically, influence, benefit, and turnover proportion stayed critical markers to foresee chapter 11 for Indian
assembling firms. Atenii and Asghari. (2020) analyzed main subjects for business and financial institutions in recent
decades the bankruptcy predicted by using both logic and genetic algorithm (GA) prediction techniques under sanctioned
circumstances. The results suggest that the two models have the capability of predicting bankruptcy and the GA model is
more accurate than the logit model in this regard. Inam et al (2019) analyzed the danger of liquidation inside the
Pakistani firms of the non-monetary area. By gathering information from Three methods which incorporate multivariate
discriminant examination (MDA), logit relapse, and multilayer perceptron counterfeit neural organizations. the data of
firms were chosen one year before the bankruptcy. The after effects of this investigation demonstrated that the neural
organizations model beats inside the forecast of chapter 11, productivity, and influence pointers have the office of
separation in insolvency expectation , and therefore the best variables to predict financial distress are also found and
indicated. Muñoz-Izquierdo et al (2019) researched numerous concentrates on chapter 11 expectation utilizing
monetary proportions, practically zero is perceived about how outer review data can add to foreseeing monetary trouble
by gathering information from the examination of review reports for forecast purposes and hence a similar prescient
exactness was accomplished by applying three AI procedures (PART calculation, irregular woodland, and backing
vector machine).The consequence of this investigation indicated that by finding the review assessment, recognizing if an
issue segment exists, and accordingly the quantity of remarks unveiled, any client may anticipate an insolvency
circumstance with a comparable precision as though that they had investigated the whole report. Gnip and Drotár.
(2019) investigated Application of the machine learning methods on strongly imbalanced datasets is a challenging task
in the field of data processing by used OCS and IF methods for comparison and analyzing the different methods.The
result of this study showed that the neural organizations model beats inside the expectation of liquidation. They further
infer that benefit and influence markers have the office of separation in liquidation forecast and in this manner the best
factors to foresee monetary pain also are found and indicated . Boughaci and Alkhawaldeh,(2020) examined in
machine learning techniques for credit scoring and bankruptcy prediction in finance and banking.By collecting data from
various methods like Bayes net method, The Logit Boost method, Ada Boost method, and Random Forest method from
different countries. The result of this study showed that the in Indian Qualitative Bankruptcy dataset, almost all the
methods are comparable. Aalbers et al (2019) examined employment retention postbankruptcy as a consequence of the
type of bankruptcy proceeding and the severity of prebankruptcy financial distress by chapter 11 procedures documented
with Dutch courts in the period 2012–2018 through the focal points of genuine choices and obligation overhang
hypothesis. The outcome demonstrated that the amount of asset slack, the safeguarding of representative worth is best
served under a pre-stuffed insolvency than a standard liquidation continuing. Khaerunnisa and Rahayu (2019)
examined the level of companies bankruptcy by applying Altman Z-Score at the manufacturing companies registered in
the Indonesia Stocks Exchange. The result indicated that Z-Score model applicable to detect the company’s potential
bankruptcy issues, especially manufacturing company subsectors of cosmetics and house appliances. Csikosova et al
(2019) examined monetary wellbeing and expectation of money related issues of the organizations , different records are
utilized which can work contribution for master assessment or making of different models utilizing multidimensional
factual techniques. The outcome demonstrated that encounters from expectation models have demonstrated their
5

moderately high forecast capacity, yet just in wonderful conditions, which can't be certified in post-socialist nations.
Shome and Verma (2020) analysed significant growth prospects on various parameters like passenger traffic, freight

Archives Available @ www.solidstatetechnology.us

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

traffic, aircraft movements and number of airports, among others the first aim of this paper is to assess the present
financial health of various Indian airline companies by collecting data from different models like Altman Modified Z”
Score Model, Pilarski Model, symbolic logic Model and Kroeze Model to check the existence of monetary distress and
simultaneously aims to assess the applicability of those models on the Indian aviation sector. The analysis contributes to
the prevailing literature on Indian aviation by attempting to point the suitability of studied models for indicating.Islam et
al (2019) researched In the era of credit risk analytics where Bankruptcy Prediction Models (BPMs) with the
availability and pool of comprehensive struggle and existing sets and the presence of greatest class disbalance in the data
that constraint of the prediction model with of collecting data on a upto the minute public dataset label Freddie Mac
Single-Family Loan-Level Dataset with resampling (i.e., adding synthetic minority samples) and other AI techniques
(e.g.,tree-based ensemble technique) . The results they discovered that models lead remarkably when given prompt
substitute in the economy (e.g., a worldwide monetary crisis)resulting in broken varieties in the public bilking rate.
Giannopoulos and Sigbjornsen (2019) contemplated review expectation capacity of insolvency forecast models for
organizations sort on the Athens Stock Exchange.By assortment information from these two models Taffler's and
Grammatikos and Gloubos' Y models. The outcomes shows most recent and accurate sign of liquidation assists
organizations with finding a way to determine monetary pressure; subsequently the Greek insolvency expectation models
will assist organizations with limiting danger. Elviani(2020) investigated Various bankruptcy to search the extreme
suitable and exact bankruptcy prediction model to be used in by studying predicting bankruptcy are trading sector
companies listed in Indonesia Stock Exchange (IDX) during the observation of 2012 to 2017 and accessed through the
website and research data were selected by using a sampling technique. Samples obtained during the observation period
was the trade sectors are 52 non-bankrupt companies and 1 bankrupt company. The results of this study showed that the
most appropriate and accurate model in predicting bankruptcy of trade sector companies in Indonesia is the Springate
model and the Altman model. García et al(2015) investigated to produce accurate prediction models by comparing the
different models for bankruptcy prediction were to tackle the issue.by examining the more than 140 papers published
journals are referred inside the interval 2000– 2013, which are foundation of the orignal structure in credit scoring and
bankruptcy prediction implementation the results solution that the abundant approach have been made to produce exact
prediction models that can tackle these issues. they allow portion warnings and guidelines for the usage of databases,
data splitting methods, performance estimation metrics, and hypothesis testing procedures to intersect on a systematic,
expected validation level. Nanda and Pendharkar (2001) illustrate how a misclassification cost matrix can be
incorporated into an evolutionary classification system for bankruptcy prediction.by using the principles of evolution to
develop and by testing a genetic algorithm (GA) based approach that incorporates the asymmetric Type I and Type II
error costs, Using simulated, real-life bankruptcy data, and by comparing the results of our proposed approach with three
linear approaches. the results showed that the lower misclassification costs while compared to the LDA and GA
approaches that do not incorporate misclassification costs. Mihalovic(2016) studded the development of bankruptcy
prediction models in Slovak companies.by comparing the forecast conducting of the two developed models are
discriminant analysis and logistic regression and collected the illustrative of 236 firms set off in Slovakia and divided
into two groups – failed and non-failed firms. The results examined that the model based on a logit function exceed the
classification accuracy of the discriminant model.
CONCLUSION
The study will be centre on deciding the finest acceptable accounting-based bankruptcy prediction for Indian base
companies by differentiating accounting-based models from previous literature. In order to estimate the performance of
these bankruptcy prediction models. To observe out which will be more used and calculate the accuracy at critical
period. In this research methodology we will be finding What is the difference in foresight power of accounting-based
bankruptcy prediction models of Altman and Ohlson to Indian companies. In order to find the What is the correctness
rate of accounting-based bankruptcy prediction models of Altman and Ohlson Indian companies? The categorization
periods used from 2001 to 2020 research papers the selected bankruptcy prediction models are good and more exact in
the execute in the past research’s.
REFERENCES
 Aalbers, H., Adriaanse, J., Boon, G. J., van der Rest, J. P., Vriesendorp, R., & Van Wersch, F. (2019). Does pre
packed bankruptcy create value? An empirical study of postbankruptcy employment retention in The Netherlands.
6

International Insolvency Review, 28(3), 320-339.

Archives Available @ www.solidstatetechnology.us

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

 Alaka, H. A., Oyedele, L. O., Owolabi, H. A., Kumar, V., Ajayi, S. O., Akinade, O. O., & Bilal, M. (2018).
Systematic review of bankruptcy prediction models: Towards a framework for tool selection. Expert Systems with
Applications, 94, 164-184.
 Alexandropoulos, S. A. N., Aridas, C. K., Kotsiantis, S. B., & Vrahatis, M. N. (2019, May). A deep dense neural
network for bankruptcy prediction. In International Conference on Engineering Applications of Neural Networks (pp.
435-444). Springer, Cham.
 Altman, E. I., Iwanicz-Drozdowska, M., Laitinen, E. K., & Suvas, A. (2014). Distressed firm and bankruptcy
prediction in an international context: A review and empirical analysis of Altman's Z-score model. Available at SSRN
2536340.
 Azayite, F. Z., & Achchab, S. (2019). A hybrid neural network model based on improved PSO and SA for bankruptcy
prediction. arXiv preprint arXiv:1907.12179.
 Bateni, L., & Asghari, F. (2020). Bankruptcy Prediction Using Logit and Genetic Algorithm Models: A Comparative
Analysis. Computational Economics, 55(1), 335-348.
 Begović, S. V., Bonić, L., & Jovin, S. (2020). a comparison of the bankruptcy prediction models on a sample of
serbian companies. teme, 503-518.
 Boughaci, D., & Alkhawaldeh, A. A. (2020). Appropriate machine learning techniques for credit scoring and
bankruptcy prediction in banking and finance: A comparative study. Risk and Decision Analysis, (Preprint), 1-10.
 Bouwmeester, A. (2020). Prediction power of accounting-based bankruptcy prediction models: evidence from Dutch
and Belgian public and large private firms (Master's thesis, University of Twente).
 Cultrera, L., & Brédart, X. (2016). Bankruptcy prediction: the case of Belgian SMEs. Review of Accounting and
Finance.
 Csikosova, A., Janoskova, M., & Culkova, K. (2019). Limitation of financial health prediction in companies from
post-communist countries. Journal of Risk and Financial Management, 12(1), 15.
 Devi,s.s & Radhika,y.(2019). an analytical approach for bankruptcy prediction using big data and machine learning.
journal of theoretical and applied information technology, 97(6).
 Elviani, S., Simbolon, R., Riana, Z., Khairani, F., Dewi, S. P., & Fauzi, F. (2020). The Accuracy of the Altman,
Ohlson, Springate and Zmejewski Models in Bankruptcy Predicting Trade Sector Companies in Indonesia. Budapest
International Research and Critics Institute (BIRCI-Journal), 3, 334-47. García, V., Marqués, A. I., & Sánchez, J. S.
(2015). An insight into the experimental design for credit risk and corporate bankruptcy prediction systems. Journal
of Intelligent Information Systems, 44(1), 159-189.
 Giannopoulos, G., & Sigbjornsen, S. (2019). Prediction of bankruptcy using financial ratios in the Greek market.
Theoretical Economics Letters, 9, 1114-1128.
 Gnip, P., & Drotár, P. (2019, September). Ensemble methods for strongly imbalanced data: bankruptcy prediction. In
2019 IEEE 17th International Symposium on Intelligent Systems and Informatics (SISY) (pp. 155-160). IEEE.
 Horak, J., Vrbka, J., & Suler, P. (2020). Support Vector Machine Methods and Artificial Neural Networks Used for
the Development of Bankruptcy Prediction Models and their Comparison. Journal of Risk and Financial Management,
13(3), 60
 Horak, J., Vrbka, J., & Suler, P. (2020). Support Vector Machine Methods and Artificial Neural Networks Used for
the Development of Bankruptcy Prediction Models and their Comparison. Journal of Risk and Financial Management,
13(3), 60.
 Inam, F., Inam, A., Mian, M. A., Sheikh, A. A., & Awan, H. M. (2019). Forecasting Bankruptcy for organizational
sustainability in Pakistan. Journal of Economic and Administrative Sciences.
7

Archives Available @ www.solidstatetechnology.us

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

 Islam, S. R., Eberle, W., Ghafoor, S. K., Bundy, S. C., Talbert, D. A., & Siraj, A. (2019). Investigating bankruptcy
prediction models in the presence of extreme class imbalance and multiple stages of economy. arXiv preprint
arXiv:1911.09858.
 Joshi, P. D. (2019). A study on application of Altman’s Z score model in predicting the bankruptcy of Reliance
Communication. International Journal of 360 Management Review, 7(02), 35-47.
 Karas, M., & Režňáková, M. (2020). Creating a new bankruptcy prediction model: The grey zone problem. In
Proceedings of the 24th IBIMA Conference: Crafting Global Competitive Economies.
 Khaerunnisa, I., & Rahayu, N. A. (2019). Analysis of bankruptcy issues at manufacturing companies, sub-sectors of
cosmetics and houseappliances registered in Indonesia Stock Exchange (IDX) year 2015-2017 using Altman Z-score.
The Accounting Journal of Binaniaga, 4(01), 27-36.
 Kovacova, M., & Kliestik, T. (2017). Logit and Probit application for the prediction of bankruptcy in
 Slovak companies. Equilibrium. Quarterly Journal of Economics and Economic Policy, 12(4), 775-791.
 Le, T., Lee, M. Y., Park, J. R., & Baik, S. W. (2018). Oversampling techniques for bankruptcy prediction: novel
features from a transaction dataset. Symmetry, 10(4), 79.
 Mihalovic, M. (2016). Performance comparison of multiple discriminant analysis and logit models in bankruptcy
prediction. Economics & Sociology, 9(4), 101.
 Muñoz-Izquierdo, N., Camacho-Miñano, M. D. M., Segovia-Vargas, M. J., & Pascual-Ezama, D. (2019). Is the
external audit report useful for bankruptcy prediction? Evidence using artificial intelligence. International Journal of
Financial Studies, 7(2), 20.
 Musah, A., & Agyirakwah, J. A. (2019). Application of Altman Bankruptcy prediction model in Ghana. Jurnal
Perspektif Pembiayaan Dan Pembangunan Daerah, 7(1), 63-72.
 Nanda, S., & Pendharkar, P. (2001). Linear models for minimizing misclassification costs in bankruptcy prediction.
Intelligent Systems in Accounting, Finance & Management, 10(3), 155-168. Ogachi, D., Ndege, R., Gaturu, P., &
Zoltan, Z. (2020). Corporate Bankruptcy Prediction Model, a Special Focus on Listed Companies in Kenya. Journal of
Risk and Financial Management, 13(3), 47.
 Ouenniche, J., Bouslah, K., Perez-Gladish, B., & Xu, B. (2019). A new VIKOR-based in-sample-outof-sample
classifier with application in bankruptcy prediction. Annals of Operations Research, 1-18.
 Prusak, B. (2019). Corporate Bankruptcy Prediction in Poland Against the Background of Foreign Experience. e-
Finanse, 15(1), 10-19.
 SHOME, S., & VERMA, S. (2020). Financial Distress in Indian Aviation Industry: Investigation Using Bankruptcy
Prediction Models. Eurasian Journal of Business and Economics, 13(25), 91-109.
 Singh, B. P., & Mishra, A. K. (2019). Sensitivity of bankruptcy prediction models to the change in econometric
methods. Theoretical & Applied Economics, 26(3).
 Singh, B. P., & Mishra, A. K. (2019). Sensitivity of bankruptcy prediction models to the change in econometric
methods. Theoretical & Applied Economics, 26(3).
 Tian, S., & Hartling, X. (2019). Is Greenhouse Gas Emission a New Player in Corporate Bankruptcy Prediction?.
Journal of Supply Chain and Operations Management, 17(2), 169.
 Tian, S., & Hartling, X. (2019). Is Greenhouse Gas Emission a New Player in Corporate Bankruptcy Prediction?.
Journal of Supply Chain and Operations Management, 17(2), 169.
 Valencia, C., Cabrales, S., Garcia, L., Ramirez, J., & Calderona, D. (2019). Generalized additive model with
embedded variable selection for bankruptcy prediction: Prediction versus interpretation. Cogent Economics &
8

Finance, 7(1), 1597956.

Archives Available @ www.solidstatetechnology.us

 Solid State Technology
Volume: 63 Issue: X
Publication Year: 2020

 Wang, M., Chen, H., Li, H., Cai, Z., Zhao, X., Tong, C., ... & Xu, X. (2017). Grey wolf optimization evolving kernel
extreme learning machine: Application to bankruptcy prediction. Engineering Applications of Artificial Intelligence,
63, 54-68.

Archives Available @ www.solidstatetechnology.us

View publication stats