The Predictability Power of Neural Network and Genetic Algorithm from Fiems’ Financial crisis

Subject Areas : Financial Econometrics

Nader  Rezaei ¹ (Department of Accounting and Finance, Maragheh Branch, Islamic Azad University, Maragheh, Iran)
Maryam  Javaheri ² (Department of Accounting and Finance, Maragheh Branch, Islamic Azad University, Maragheh, Iran)

Received: 2019-03-05 Accepted : 2019-04-30 Published : 2020-04-01

Keywords: Genetic Algorithm, Artificial Neural Network, financial crisis,

Abstract :

Organizations expose to financial risk that can lead to bankruptcy and loss of business is increased nowadays. This may leads to discontinuity in operations, increased legal fees, administrative costs and other indirect costs. Accordingly, the purpose of this study was to predict the financial crisis of Tehran Stock Exchange using neural network and genetic algorithm. This research is descriptive and practical and in order to collect data Stock Exchange database software has been used. For data analysis, we used artificial neural network in base form and artificial neural network mix with genetic algorithm. In addition for methods comparison, determination coefficient, Mean squared error and Root-mean square error have been used. The result of study shows that the best artificial neural network is a network with a hidden layer and eight neurons in the layer. This network could predict 97.7 percent of healthy and bankrupt companies correctly for test data. Furthermore the best mixed neural network with genetic algorithm is a network with 400 replications and population size 50, one layer and eight neurons which could correctly predict 100% of healthy and bankrupt companies. Finally, comparison of results of two methods shows that the best method for predicting financial crisis is mixed neural network with genetic algorithm.

References:

[1] Rezaei, N., and Elmi, Z., Behavioral finance models and behavioral biases in stock price forecasting, Advances in mathematical finance and applications, 2018, 3 (4), P.67-82. DOI: 10.22034/AMFA.2019.576127.1118

 [2] Adnan, A. M., and Humayon, D., Predicting Corporate Bankruptcy, Department of Economics, Loughborough University, UK, 2002. DOI: 10.1108/14720700610649436

 [3] Saghafi, A., and  Amiri, G. A., Investigating the Indicators of Bankruptcy Predictors in Iran's Environment, Ph.D. thesis, Faculty of Management Tehran University, Tehran, Iran, 2003, (in Persian).

 [4] Dibachi, H., Behzadi, M.H., Izadikhah, M., Stochastic multiplicative DEA model for measuring the efficiency and ranking of DMUs under VRS technology, Indian Journal of Science and Technology,2014, 7 (11), P. 1765–1773.

 [5] Dibachi, H., Behzadi, M.H., Izadikhah, M., Stochastic Modified MAJ Model for Measuring the Efficiency and Ranking of DMUs, Indian Journal of Science and Technology,2015, 8 (8), P. 549–555.

 [6] Mohseni, R., and Rahimian, S. Y., Investigating the Factors Affecting Bankruptcy Using Efficiency as a Predictive Variable Based on Data Logic Panel Approach, Journal of Quantities Economics, 2018, 15 (2), P.111-130, (in Persian). DOI: 10.22055/JQE.2018.23087.1711

 [7] Pereira, J., Survival analysis employed in predicting corporate failure: A forecasting model proposal. IBR, 2014, 7 (5), P.9-22. DOI:10.5539/ibr.v7n5p9

 [8] Miryekemami, S. A., Sadeh, E., and Amini, Z, S., Using Genetic algorithm in solving stochastic programming for multi-objective portfolio selection in Tehran stock exchange, Advances in mathematical finance and applications, 2017, 2 (4), P.107-120. DOI: 10.22034/AMFA.2017.536271

 [9] Azar, A., Hamidian, M., Saberi, M., and Norozi, M., Evaluating the performance of forecasting models for portfolio allocation purposes with generalized GRACH method, Advances in mathematical finance and applications,2017, 2 (1), P.1-7. DOI: 10.22034/AMFA.2017.529057

 [10] Richards, C. A., The effect of hospital financial distress on immediate breast reconstruction. Ph.D. thesis, Columbia University, New York, USA. DOI:10.7916/D8C53HZ2

 [11] Rosenberg H. J., and Ferlie, E., Applying strategic management theories in public sector organizations: Developing a typology, Public Management Review, 2014, 18 (1), P.1-19. DOI:10.1080/14719037.2014.957339

 [12] Geng, R., Bose, I., and Chen, X., Prediction of financial distress: An empirical study of listed Chinese companies using data mining, European Journal of Operational Research, 2014, 241 (1), P.236-247. DOI:10.1016/j.ejor.2014.08.016

 [13] Nazemi, A. M., and Zare, M. V., Bankruptcy prediction of companies according to industry characteristics, Quarterly journal of accounting research, 2017, 7 (2), P.122-139, (in Persian).

DOI:10.22051/ijar.2017.10856.1174

 [14] Ghazanfari, M., Eghbal, R., and Asgari, A., Bankruptcy prediction of companies based on hybrid smart systems, Financial Accounting and Auditing Research, 2018, 10 (27), P.159-193, (in Persian).

 [15] Saeidi, A., and Aghaei, A., The prediction of financial distress among companies accepted in the Tehran Stock Exchange using bayes networks, Accounting and auditing reviews, 2009, 16 (56), P.59-78, (in Persian).

 [16] Saruei, S., The study of performance of Springerit, Zimsky and Ahlson models in predicting bankruptcy of companies accepted in Tehran Stock Exchange, M. A. thesis, Arak Islamic Azad University, Arak, Iran, (2010), (in Persian).

 [17] Asgari, H., Study of the Efficiency of Springerit, Zowin and Fuler Patterns in Bankruptcy Forecast of Companies Accepted in Tehran Stock Exchange, M.A. thesis, Islamic Azad University, Tehran Central Branch, Tehran, Iran, 2010, (in Persian).

 [18] Ghadiri, A., Golampourfard, M., and Nasirzadeh, F., Investigating the ability of Altman and Ohlson bankruptcy prediction models following the bankruptcy of the companies listed in the stock exchange, Journal of Knowledge and Development, 2009, 16 (28), P.193-220, (in Persian).

 [19] Raei, R., and Fallahpour, S., The prediction of financial distress for companies using artificial neural networks, Financial research, 2004, 17, (in Persian).

 [20] Shariatpanahi, M., and Araghi, S. M., Providing a model for predicting financial crisis in Iranian companies. Empirical studies on financial accounting, 2006, 4(16), P.19-41, (in Persian).

 [21] Farajzadeh, H. D., Application of Genetic Algorithms in Bankruptcy Forecast Modeling, M.A. thesis, Tarbiat Modarres University, Tehran, Iran, 2007, (in Persian).

 [22] Ahadidolatsara, R., The Effectiveness of Financial Crisis Forecast Models Using Financial Ratios in Iran's Economic Environment. M.A. thesis, Alzahra University, Tehran, Iran, 2008, (in Persian).

 [23] Poormehr, S., Investigating the feasibility of using Springerit and Zemjiecki patterns in predicting bankruptcy of companies admitted to Tehran Stock Exchange,  M. A. thesis, Islamic Azad University, Tehran Central Branch, Tehran, Iran, 2007, (in Persian).

 [24] Hosaka, T.,  Bankruptcy prediction using imaged financial ratios and convolution neural networks. Expert systems with applications, 2019, 117, P.287-299. DOI:10.1016/j.eswa.2018.09.039

 [25] Feng, M., Shaonan, T.. Chihoon, L., and Ling, M., Deep learning models for bankruptcy prediction using textual disclosures, European journal of operational research, 2019, 274 (2), P.743-758. DOI:10.1016/j.ejor.2018.10.024

 [26] Chen, J. M., Models for Predicting Business Bankruptcies and Their Application to Banking and to Financial Regulation, Available at SSRN: https://ssrn.com/abstract=3329147, 2019, DOI:10.2139/ssrn.3329147

 [27] Zeiba, M., Tomczak, S. K., and Tomczak, M., Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction. Expert systems with applications, 2016, 58, P.93-101. DOI:10.1016/j.eswa.2016.04.001

 [28] Cho, S., Kim, W., and Ba, J., An integrative model with subject weight based on neural network learning for bankruptcy prediction, Expert Systems with applications, 2009, 36, P.403-410.

 [29] Hyun-Jung, K., Nam-Ok, J., and Kyung-shik, S., Optimization of cluster-based evolutionary under sampling for the artificial neural networks in corporate bankruptcy prediction, Expert systems with applications, 2016, 59, P.226-234. DOI:10.1016/j.eswa.2016.04.027

 [30] Chandra, K., Ravi, V., and Bose, I., Failure prediction of dotcom companies using hybrid intelligent techniques, Expert Systems with applications, 2006, 36 (3), P.4830-4837. DOI:10.1016/j.eswa.2008.05.047

 [31] Analyzing the financial distress of Chinese public companies using probabilistic neural networks and multivariate discriminate analysis, Socio-economic planning science, 42 (3) P.206-220. DOI:10.1016/j.seps.2006.11.002

 [32] Chuang, L. C.,  Application of hybrid case-based reasoning for enhanced performance in bankruptcy prediction, Information Science, 2013, 236, P.174-185. DOI:10.1016/j.ins.2013.02.015

 [33] Cochran, J., and Darrat, Kh. E., Bankruptcy of internet Companies: An Empirical Inquiry, Journal of Business Research, 2006, 59, P.1193-1200.

 [34] Tsakonas A., Dounias G., Doumpos M., and Zopounidis, C., Bankruptcy Prediction with Neural Logic Networks by Means of Grammar-Guided Genetic Programming, Expert Systems with Applications, 2006, 30, P.449-461.

 [35] Wallace Wanda A. Risk Assessment by Internal Auditors Using Past Research on Bankruptcy Applying Bankruptcy Models, 2004.

 [36] Mazumder, B., and Miller, S., The effects of the Massachusetts health reform on financial distress, Working Paper, Federal Reserve Bank of Chicago. DOI:10.2139/ssrn.2390186