Abstract

This paper aims to focus on the comparison of the artificial neural network model and logistic regression model in the prediction of companies’ bankruptcy in Tehran stock exchange (TSE) in 3,2 and 1 year in advance. This study exercises an analytic-mathematical approach which has been utilized three-layer artificial neural network tools, which includes one hidden layer and one output neuron and logistic regression (LR) with seven independent variable and one dependent variable for testing research’s hypotheses. Although the given results illustrates the high potential capacities of both models in the prediction of bankruptcies in an interval of three years, two years and one year before bankruptcy, capacity of neural network model showed the relative higher capability than LR model. This study takes into consideration the comparison of two popular tools of artificial neural networks (ANNs) and LR in bankruptcy prediction that are of importance in their own type.

Keyword

Logistic regression (LR), Artificial neural networks (ANNs), Tehran stock exchange (TSE), Bankruptcy prediction.

Cite this article

Refference

[1][1]Saghafi A. Evaluation of bankruptcy predicting factors in Iranian environmental. PhD thesis, Tehran University. 2002.

[2][2]Lee KC, Han I, Kwon Y. Hybrid neural network models for bankruptcy predictions. Decision Support Systems. 1996; 18(1):63-72.

[3][3]Gordon MJ. Towards a theory of financial distress. The Journal of Finance. 1971; 26(2):347-56.

[4][4]Whitaker RB. The early stages of financial distress. Journal of Economics and Finance. 1999; 23(2):123-32.

[5][5]Weston JF, Brigham EF. Essentials of managerial finance. Dryden Press; 1990.

[6][6]Shah JR, Murtaza MB. A neural network based clustering procedure for bankruptcy prediction. American Business Review. 2000;18(2):80-6.

[7][7]Newton GW. Bankruptcy and insolvency accounting, practice and procedure. John Wiley & Sons; 2009.

[8][8]Odom MD, Sharda R. A neural network model for bankruptcy prediction. In international joint conference on neural networks 1990 (pp. 163-8).

[9][9]Zhang G, Hu MY, Patuwo BE, Indro DC. Artificial neural networks in bankruptcy prediction: General framework and cross-validation analysis. European Journal of Operational Research. 1999;116(1):16-32.

[10][10]Ahn BS, Cho SS, Kim CY. The integrated methodology of rough set theory and artificial neural network for business failure prediction. Expert Systems with Applications. 2000; 18(2):65-74.

[11][11]Adnan Aziz M, Dar HA. Predicting corporate bankruptcy: where we stand? Corporate Governance: The International Journal of Business in Society. 2006; 6(1):18-33.

[12][12]Pendharkar PC. A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem. Computers & Operations Research. 2005; 32(10):2561-82.

[13][13]McKendrick JH. Statistical analysis using SPSS. Key Methods in Geography. 2003:425-43.

[14][14]Ohlson JA. Financial ratios and the probabilistic prediction of bankruptcy. Journal of Accounting Research. 1980; 18(1):109-31.

[15][15]Beaver WH. Financial ratios as predictors of failure. Journal of Accounting Research.1966 :71-111.

[16][16]Springate GL. Predicting the possibility of failure in a Canadian firm: A discriminant analysis (Doctoral dissertation, Simon Fraser University). 1978.

[17][17]Salchenberger LM, Cinar E, Lash NA. Neural networks: A new tool for predicting thrift failures*. Decision Sciences. 1992;23(4):899-916.

[18][18]Tam KY, Kiang MY. Managerial applications of neural networks: the case of bank failure predictions. Management Science. 1992;38(7):926-47.

[19][19]Fulmer JG, Moon JE, Gavin TA, Erwin JM. A bankruptcy classification model for small firms. Journal of Commercial Bank Lending. 1984;14:25-37.