Skip to main content
SpringerLink
Log in

Artificial neural networks and bankruptcy forecasting: a state of the art

  • Original Article
  • Published:
Neural Computing & Applications Aims and scope Submit manuscript

Abstract

The use of neural networks in finance began by the end of the 1980s and by the beginning of the 1990s, it developed specific applications related to forecasting on the failure of companies. In order to highlight the evolution of this research stream, we have retained and analysed 30 studies in which the authors use neural networks to solve companies’ classification problems (healthy and failing firms). This review of all these works gives us the opportunity to stress upon future trends in bankruptcy forecasting research.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Notes

  1. The class of sound companies cannot be separated from the class of failing companies by a linear form, as both classes overlap.

  2. The multivariate discriminant analysis was a data analysis tool used within the scope of the bankruptcy forecast by E.I. Altman in 1968. For further information, please see Casta and Zerbib (1979).

  3. For further information on the various artificial neural networks, please refer to Blayo and Veleysen (1996).

  4. The « pruning » techniques aim at helping the construction of artificial neural networks. From a given neural architecture, some neurons will be phased out provided the network achieves the same performance, thereby giving the most simple combination.

  5. For a review of the literature about the bankruptcy theory, please refer to Scott (1980), Degos (1991) and Malécot (1991).

References

  • Alici Y (1994) Neural networks in corporate failure prediction: the UK experience

  • Altman EI, Marco G, Varetto F (1994) Corporate distress diagnosis: comparisons using linear discriminant analysis and neural networks (the Italian experience). J Banking Finance 18:505–529

    Article  Google Scholar 

  • Bardos M et Zhu W (1997) Comparaison de l’analyse discriminante linéaire et des réseaux de neurones: application à la détection de défaillance d’entreprises, Revue de Statistique Appliquée 45(4)

  • Blayo F et Verleysen M (1996) Les réseaux de neurones artificiels, collection Que-sais-je ?, PUF

  • Boritz JE, Kennedy DB (1995), Effectiveness of neural network types for prediction of business failure. Expert Syst Appl 9(4):503–512

    Article  Google Scholar 

  • Casta JF et Prat B (1994) Approche connexionniste de la classification des entreprises: contribution au traitement d’informations incomplètes. Congrès de l’Association Française de Comptabilité, Paris IX Dauphine

  • Casta JF et Zerbib JP (1979) Prévoir la défaillance des entreprises ?, Revue Française de Comptabilité, Octobre, pp 506–527

  • Coats PK, Fant LF (1993) Recognizing financial distress patterns using a neural network tool, financial management. Autumn, pp 142–155

  • Coleman KG, Graettinger TJ, Lawrence WF (1996) Neural networks for bankruptcy prediction: the power to solve financial problems, in NN in finance and investing: using AI to improve real-world performance TRIPPI/TURBAN. Irwin Professional Publishing, revised 1996, pp 261–266, première parution dans AI review July, August 1991, pp 48–50

  • Cottrell M et Gaubert P (1998) Classification des chômeurs récurrents et sorties de chômage, Journée ACSEG’98, Louvain-la-Neuve

  • De Almeida FC, Dumontier P (1993) Neural networks, accounting numbers and bankruptcy prediction, Congrès de l’Association Française de Comptabilité. Comptabilité et Nouvelles Technologies, Mai, pp 269–286

    Google Scholar 

  • Degos JG (1991) Le diagnostic financier de la PME: de l’image à l’enjeu, Thèse, Université de Bordeaux I

  • Dorsey RE, Edmister RO, Johnson JD (1995) Bankruptcy prediction using artificial neural systems, working paper. University of Mississipi, School of Business

  • Dumontier P (1990) Vices et vertus des modèles de prévision de défaillance, Papier de recherche N° 90–12, Université de Grenoble II, CERAG

  • Erxeleben K, Koch H (1991) Früherkennung von Unternehmenskrisen-ein Vergleich von neuronalen netzen und Diskriminanzanalyse, working paper, Universität Erlangen-Nürnberg, Abteilung Wirtschaftsinformatik

  • Etheridge HL, Sriram RS, Hsu HYK (2000) A comparison of selected artificial neural networks that help auditors evaluate client financial viability Spring 2000. Decis Sci 31(2):531–550

    Article  Google Scholar 

  • Fioleau B (1992), Efficacité et risque d’exploitation: application aux entreprises du secteur agricole, Thèse de Sciences de Gestion, Université de Nantes, Facultés des Sciences Economiques

  • Girosi F et Poggio T (1990) Networks and the best approximation property. Biol Cybern 63:169–176

    Article  Google Scholar 

  • Hekanaho J, Back B, Sere K, Laitinen T (1998) Analysing bankruptcy data with multiple methods, working paper, Association for Artificial Intelligent

  • Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366

    Article  Google Scholar 

  • Kerling M (1994) Corporate distress diagnosis: an international comparison, pp 407–422

  • Kiviluoto K, Bergius P (1997) Exploring corporate bankruptcy with two-level self organizing map, decision technologies for financial engineering. In: Proceedings of the 13th international Congress on neural networks in the capital markets, NNCM’97

  • Kohonen T (1989) Self organization and associative memory. Springer, Berlin Heidelberg New York

    Google Scholar 

  • Martin-del-Brio B, Serrano-Cinca C (1995) Self-organizing neural networks: the financial state of Spanish companies. In: Apostolos-Paul Refenes (ed) Neural networks in the capital markets, pp 341–357

  • Malécot JF (1991) Analyses théoriques des défaillances d’entreprises: une revue de la littérature, La revue d’économie financière, N°19, Hiver, pp 205–226

  • Odom A, Sharda R (1990) A neural network model for bankruptcy prediction. In: Trippi RR, Turban E (eds) Neural networks in finance and investing, Probus Publishing, pp 177–186, originally presented at the IJCNN Meetings

  • Pedersen PE (1996) Validating a connectionist model of financial diagnosis decision technologies for financial engineering. In: Proceedings of the 4th international congress on neural networks in the capital markets NNCM’96, pp 138–150

  • Poddig T (1992) Bankruptcy prediction: a comparison with discriminant analysis. In: Apostolos-Paul Refenes (ed) Neural networks in the capital markets, 1995, pp 311–323

  • Raghupathi W, Schkade LL, Raju BS (1996) A neural network approach to bankruptcy prediction, NN in finance and investing: using AI to improve real-world performance TRIPPI/TURBAN. Irwin Professional Publishing, revised 1996, pp 227–241, première parution dans. In: Proceedings of the IEEE 24th annual Hawaii international conference on systems sciences, 1991

  • Rahimian E, Singh S, Thammachote T, Virmani R (1996) Bankruptcy prediction by neural networks, neural networks in finance and investing: using AI to improve real-world performance TRIPPI/TURBAN. Irwin Professional Publishing, revised 1996, pp 243–255

  • Rumelhart DE, Hinton GE, Williams J (1986) Learning internal representation by error propagation, In: Rumelhart DE, McClelland JC, The PDP research group (eds) Parallel distributed processing: explorations in the Microstructure of Cognition, vol 1: foundations. The MIT Press, Cambridge

  • Salchenberger LM, Cinar M, Lash NA (1996) Neural networks: a new tool for predicting thrift failures, NN in finance and investing: using AI to improve real-world performance TRIPPI/TURBAN. Irwin Professional Publishing, revised 1996, pp 303–327, première parution in Decision Science Vol 23, N° 4, July/August 1992, (899–916)

  • Scott J (1980) The probability of bankruptcy: a comparison of empirical predictions and theoretical models. J Banking Finance 5:317–344

    Article  Google Scholar 

  • Shah JR, Murtaza MB (2000) A neural network based clustering procedure for bankruptcy prediction, American Business Review, June 2000, pp 80–86

  • Tam KR, Kiang MY (1992) Managerial applications of neural networks: the case of bank failure prediction. Manage Sci 38(7):926–947

    Article  MATH  Google Scholar 

  • Tan CNW (1996) A study on using ANN to develop an early warning predictor for credit union financial distress with comparison to the Probit Model, neural networks in finance and investing: using AI to improve real-world performance, TRIPPI/TURBAN. Irwin Professional Publishing, revised, pp 329–365

  • Tilmont D (1998) Le pronostic de défaillance des petites entreprises par réseau de neurones, Colloque CIFPME, Nancy-Metz, 22–24 octobre 1998

  • Tsukuda J, Baba SI (1994) Predicting Japanese corporate bankruptcy in terms in financial data using neural networks Comput Ind Eng 27(1–4):445–448

    Article  Google Scholar 

  • Udo G (1993) Neural network performance on the bankruptcy classification problem. Comput Ind Eng 25(1–4):377–380

    Article  Google Scholar 

  • Wilson RL, Sharda R (1994) Bankruptcy prediction using neural networks. Decis Support Syst 11:545–557

    Article  Google Scholar 

  • Wu X, Flitman A (1999) Using an evolutionary neural network to predict business failure, computational intelligence for modelling, control and automation. IOS Press, Amsterdam, pp 226–231

  • Yang ZR, James H, Packer A (1997), The failure prediction of UK private construction companies, working paper. University of Portsmouth, Department of land and construction management

Download references

Author information

Authors and Affiliations

  1. Maître de conférences Préactis, Université Jean Monnet, Saint-Etienne 2, rue Tréfilerie, 42023, Saint-Etienne, France

    Muriel Perez

Authors
  1. Muriel Perez
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Muriel Perez.

Appendix

Appendix

Tables 1, 2, 3, 4, 5

Table 1 Multi-layer perceptron and back propagation algorithm
Full size table
Table 2 Multi-layer perceptron and different learning algorithms
Full size table
Table 3 The Multi-layer perceptron and other artificial neural networks
Full size table
Table 4 Kohonen self-organizing maps
Full size table
Table 5 French applications
Full size table

Rights and permissions

Reprints and permissions

About this article

Cite this article

Perez, M. Artificial neural networks and bankruptcy forecasting: a state of the art. Neural Comput & Applic 15, 154–163 (2006). https://doi.org/10.1007/s00521-005-0022-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-005-0022-x

Keywords

Search

Navigation