A comparison of supervised and unsupervised neural networks in predicting bankruptcy of Korean firms
Expert Systems with ApplicationsPublished 11 February 2005
Ki Bong Lee, David Booth, Pervaiz Alam
Citations216
SJR quartileQ1
SJR score1.85
SNIP2.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The findings suggest that the BP network is a better choice when a target vector is available than the Kohonen self-organizing feature map in the area of bankruptcy prediction.
Abstract
In this study, two learning paradigms of neural networks, supervised versus unsupervised, are compared using their representative types. The back-propagation (BP) network and the Kohonen self-organizing feature map, selected as the representative type for supervised and unsupervised neural networks, respectively, are compared in terms of prediction accuracy in the area of bankruptcy prediction. Discriminant analysis and logistic regression are also performed to provide performance benchmarks. The findings suggest that the BP network is a better choice when a target vector is available.
Keywords
Computer ScienceBusiness, Management and Accounting
Neural NetworksMultilayer feedforward networks are universal approximators
21,248 Citations1989Kurt Hornik, Maxwell B. Stinchcombe +1 more
It is rigorously established that standard multilayer feedforward networks with as few as one hidden layer using arbitrary squashing functions are capable of approximating any Borel measurable function from one finite dimensional space to another to any desired degree of accuracy, provided sufficiently many hidden units are available.
Springer series in information sciencesSelf-Organizing Maps
10,377 Citations1997Teuvo Kohonen
The mathematical preliminaries, background, basic ideas, and implications of the Self-Organising Map algorithm are expounded in a manner which is accessible without prior expert knowledge.
Biological CyberneticsSelf-organized formation of topologically correct feature maps
9,519 Citations1982Teuvo Kohonen
In a simple network of adaptive physical elements which receives signals from a primary event space, the signal representations are automatically mapped onto a set of output responses in such a way that the responses acquire the same topological order as that of the primary events.
Journal of Accounting ResearchFinancial Ratios and the Probabilistic Prediction of Bankruptcy
6,037 Citations1980James A. Ohlson
Neural NetworksOn the approximate realization of continuous mappings by neural networks
4,220 Citations1989Ken-ichi Funahashi
It is proved that any continuous mapping can be approximately realized by Rumelhart-Hinton-Williams' multilayer neural networks with at least one hidden layer whose output functions are sigmoid functions.
Management ScienceManagerial Applications of Neural Networks: The Case of Bank Failure Predictions
1,124 Citations1992Kar Yan Tam, Melody Y. Kiang
Empirical results show that neural nets is a promising method of evaluating bank conditions in terms of predictive accuracy, adaptability, and robustness.
A neural network model for bankruptcy prediction
847 Citations1990Marcus D. Odom, Ramesh Sharda
A comparison of the predictive abilities of both the neural network and the discriminant analysis method for bankruptcy prediction shows that neural networks might be applicable to this problem.
Transportation Research Part C Emerging TechnologiesCombining kohonen maps with arima time series models to forecast traffic flow
840 Citations1996Mascha C. van der Voort, Mark Dougherty +1 more
A hybrid method of short-term traffic forecasting is introduced; the KARIMA method, which uses a Kohonen self-organizing map as an initial classifier; each class has an individually tuned ARIMA model associated with it.
Decision Support SystemsBankruptcy prediction using neural networks
721 Citations1994Rick L. Wilson, Ramesh Sharda
The study indicates that neural networks perform significantly better than discriminant analysis at predicting firm bankruptcies, and implications for the accounting professional, neural networks researcher and decision support system builders are highlighted.
European Journal of Operational ResearchArtificial neural networks in bankruptcy prediction: General framework and cross-validation analysis
663 Citations1999Guoqiang Zhang, Michael Y. Hu +2 more
A comprehensive review of neural network applications in this area is given and the link between neural networks and traditional Bayesian classification theory is illustrated, indicating that neural networks are significantly better than logistic regression models in prediction as well as classification rate estimation.
Decision SciencesNeural Networks: A New Tool for Predicting Thrift Failures*
534 Citations1992Linda Salchenberger, E. Mine Çinar +1 more
A neural network model that processes input data consisting of financial ratios is developed to predict the financial health of thrift institutions and its ability to discriminate between healthy and failed institutions is compared to a traditional statistical model.
Medical Entomology and ZoologyOut of Control: The New Biology of Machines, Social Systems, and the Economic World
398 Citations1992Kevin T. Kelly
The Butterfly Sleeps, Rising Flow, Prediction Machinery, Wholes, Holes, and Spaces, and The Nine Laws of God are presented.
Unsupervised learning : foundations of neural computation
273 Citations1999Geoffrey E. Hinton, Terrence J. Sejnowski
Expert Systems with ApplicationsBankruptcy prediction using case-based reasoning, neural networks, and discriminant analysis
272 Citations1997Hongkyu Jo, Ingoo Han +1 more
Three different techniques are used: Multivariate discriminant analysis, case-based forecasting, and neural network to predict Korean bankrupt and nonbankrupt firms, with good results.
Decision Support SystemsSelf organizing neural networks for financial diagnosis
238 Citations1996Carlos Serrano‐Cinca
A complete Decision Support System for financial diagnosis based on Self Organizing Feature Maps (SOFM) provides a complete analysis which goes beyond that of the traditional models based on the construction of a solvency indicator also known as Z score, without renouncing simplicity for the final decision maker.
Expert Systems with ApplicationsEffectiveness of neural network types for prediction of business failure
201 Citations1995J. Efrim Boritz, Duane B. Kennedy
The study examines the effectiveness of different neural networks in predicting bankruptcy filing and demonstrates that the performance of the neural networks tested is sensitive to the choice of variables selected and that the networks cannot be relied upon to “sift through” variables and focus on the most important variables.
Decision SciencesThe Application of Neural Networks and a Qualitative Response Model to the Auditor's Going Concern Uncertainty Decision*
154 Citations1995Mary Jane Lenard, Pervaiz Alam +1 more
The generalized reduced gradient (GRG2) optimizer for neural network learning, a backpropagation neural network, and a logit model are used to predict which firms would receive audit reports reflecting a going concern uncertainty modification.
NeurocomputingPredicting bankruptcies with the self-organizing map
138 Citations1998K. Kiviluoto
The phenomenon of going bankrupt is analyzed qualitatively, and companies are also classified into healthy and bankrupt-prone ones and a modification of the learning vector quantization algorithm to accommodate the Neyman–Pearson classification criterion.
Expert Systems with ApplicationsThe use of fuzzy clustering algorithm and self-organizing neural networks for identifying potentially failing banks: an experimental study
125 Citations2000Pervaiz Alam, David E. Booth +2 more
The findings indicate that both the fuzzy clustering and self-organizing neural networks are promising classification tools for identifying potentially failing banks.
Intelligent Systems in Accounting Finance & ManagementUsing neural networks to predict corporate failure
115 Citations1998Daniel E. O’Leary
John Wiley & Sons, Inc. eBooksNeural Networks in the Capital Markets
101 Citations1994A.N. Refenes
The author takes a pragmatic view of neural networks, treating them as computationally equivalent to well-understood, non-parametric inference methods in decision science and makes comparisons with established techniques where appropriate.
Computers & Industrial EngineeringNeural network performance on the bankruptcy classification problem
78 Citations1993Godwin Udo
Artificial neural network technology is used to predict the going concern of firms based on financial ratios of 300 companies and results indicate that ANN is as accurate or more accurate as a multiple regression model in predicting bankruptcy in addition to being easier to use and readily adapting to the changing environment.
Computers & Industrial EngineeringPredicting japanese corporate bankruptcy in terms of financial data using neural network
57 Citations1994Junsei Tsukuda, Shinichi Baba
This study investigated the effectiveness of a neural network with one hidden layer as a bankruptcy prediction system using only financial data for 1 and 3 years prior to failure to show equivalence of both techniques for listed firms and for unlisted firms.
Journal of ManagementAn Empirical Critique of In Search of Excellence: How Excellent are the Excellent Companies?
49 Citations1986Kenneth E. Aupperle, William Acar +1 more
International Journal of Operations & Production ManagementA Robust Multivariate Statistical Procedure for Evaluation and Selection of Industrial Robots
45 Citations1992David E. Booth, Moutaz Khouja +1 more
A decision model for the robot selection problem is proposed using both a robustified Mahalanobis distance analysis, i.e. a multivariate distance measure, and principal‐components analysis, and takes into consideration the fact that a robot′s performance, as specified by the manufacturer, is often unobtainable in reality.
Decision SciencesAn Analysis of Fuzzy Clustering and a Hybrid Model for the Auditor's Going Concern Assessment*
41 Citations2000Mary Jane Lenard, Pervaiz Alam +1 more
This study provides a description and testing of fuzzy clustering and a hybrid model that can support the decision an auditor makes when completing the going concern evaluation.
Analytica Chimica ActaElectrochemical characteristics of a carbon-based thick-film l-lactate biosensor using l-lactate dehydrogenase
40 Citations1996Hyun C. Yoon, Hak‐Sung Kim
International Journal of Pediatric OtorhinolaryngologyNeuronal networks and self-organizing maps: new computer techniques in the acoustic evaluation of the infant cry
34 Citations1996R. Schönweiler, S. Kaese +3 more
Recorded cries of newborns and young infants revealed similarities of different cries of the same children as well as interindividual differences, which are also audible to experienced listeners, and neuronal networks may be helpful in the early diagnosis of infant diseases.
Analytica Chimica ActaKohonen neural network as a pattern recognition method based on the weight interpretation
33 Citations1996Xin‐Hua Song, Philip K. Hopke
An alternative method is proposed for the Kohonen neural network to be used in a supervised way based on the weight interpretation (Kohonen-WI), where the membership of the samples hitting the empty neurons during the prediction process is determined to be the same as that of the nearest active neuron based on a distance measure from the trained weight vectors.
Decision SciencesA Robust Multivariate Procedure for the Identification of Problem Savings and Loan Institutions*
24 Citations1989David E. Booth, Pervaiz Alam +2 more
Pattern Recognition3D object classification using multi-object kohonen networks
20 Citations1996J.M. Corridoni, Alberto Del Bimbo +1 more
The problem of three-dimensional planar-faced opaque object recognition from one single perspective view, is addressed in this paper and a view parameterization, based on Hough Transform, is described.
Linear and nonlinear time series forecasting with artificial neural networks
16 Citations1998Guoqiang Zhang, B. Eddy Patuwo +1 more
The study first integrates previous research and identifies key issues in modeling ANNs for time series forecasting, then the effects of several major factors on the modeling and forecasting performance of neural networks are examined through an extensive simulation study.
Journal of Chemical Information and Computer SciencesA Neural Network Approach to the Detection of Nuclear Material Losses
14 Citations1996James H. Hamburg, David E. Booth +1 more
Various methods, especially neural networks, will be examined with respect to their use to detect nuclear material diversions or losses more rapidly and accurately than currently used methods.
Information SciencesFuzzy kohonen network for the classification of transients using the wavelet transform for feature extraction
14 Citations1995Christopher J. Deschenes, J.P. Noonan
The proposed transients are perturbed by multiplicative noise, and are embedded in various noise backgrounds to simulate an undersea environment, and the system is shown to be able to classify signals down to -1 dB.
Improved clustering and classification algorithms for the Kohonen self-organizing neural network
13 Citations1994Mohamed Abdalla Nour
Two improved versions of the standard Kohonen learning algorithm are proposed, tested, and compared with the standard version, and both modified versions are based on a new network architecture that serves as a point of departure from thestandard Kohonen self-organizing model.
Decision SciencesTHE ANALYSIS OF OUTLYING DATA POINTS USING ROBUST REGRESSION: A MULTIVARIATE PROBLEM‐BANK IDENTIFICATION MODEL*
11 Citations1982David E. Booth
Combining the use of the M-estimator robust regression procedure and the robust Mahalanobis distance procedure with principal components analysis is demonstrated to be a general method of outlier detection.
Journal of Chemical Information and Computer SciencesThe Use of Robust Smoothers in Nuclear Material Safeguards
6 Citations1997John Grznar, Booth +1 more
It is shown that a set of robust smoothers also produces equivalent methods that can be used in nuclear material safeguards algorithms, and that these smoothers are somewhat more sensitive to loss points than the previously studied smoothers.
An investigation of neural network ensemble methods for posterior probability estimation
1 Citations1998Victor L. Berardi, Eddy Patuwo +1 more
This dissertation investigates the performance of neural network ensembles in estimating posterior probabilities and indicates that neural networkEnsembles can improve posterior probability estimation compared to the common practice of using a single network.