BAYESIAN NETWORK MODEL OF TURKISH FINANCIAL MARKET FROM YEAR-TO-SEPTEMBER 30TH OF 2016

Year 2019, Volume: 37 Issue: 4, 1496 - 1511, 01.12.2019

Ersin Sener , Hasan Aykut Karaboga Ibrahim Demır

Abstract

Bayesian Networks (BNs) are a useful graphical probabilistic structure for visualizing and understanding the dependencies of random variables. In this study, July 15 coup attempts’ effects on Turkish Financial Market are analyzed with the BN approach. To this end, 31 Istanbul Stock Exchange (BIST) return indexes and seven foreign exchange rates (CNY, EUR, GBP, JPY, SAR, RUB, and USD) from year-to-September 30th of 2016 are examined. BN structure is learned (predict) via Greedy Thick Thinning algorithm with K2 prior from the dataset and is expertized. BN model is validated and trained from real dataset instead of generated data from the established model. The BN is called Trained Bayesian Network (TBN) model. TBN is validated and the beliefs of TBN are updated again by dataset via learning parameters with Expectation Maximization (EM) algorithm. BNs have not before been used to relate the presence/absence of BIST return indexes with foreign exchange rates. Accuracy rate (AUC) of the TBN model to generating the real data is calculated as 85.5% percent. TBN model has simplified the Market relations with conditional probability.

Keywords

Bayesian network, structure learning, Istanbul stock exchange return indexes, foreign exchange rate, Receiver Operating Characteristic (ROC).

References

• [1] Chickering, D. M. (2002): Learning equivalence classes of Bayesian-network structures. Journal of machine learning research, 2(Feb): 445-498.
• [2] Neapolitan, R. E. (2004): Learning Bayesian networks (Vol. 38). Upper Saddle River, NJ: Pearson Prentice Hall.
• [3] Aghaie, A.- Saeedi, A. (2009, April): Using Bayesian networks for bankruptcy prediction: Empirical evidence from Iranian companies. In Information Management and Engineering, 2009. ICIME'09. International Conference on: 450-455. IEEE.
• [4] Sun, L.- Shenoy, P. P. (2007): Using Bayesian networks for bankruptcy prediction: Some methodological issues. European Journal of Operational Research, 180(2): 738-753.
• [5] Sarkar, S.- Sriram, R. S. (2001): Bayesian models for early warning of bank failures. Management Science, 47(11):1457-1475.
• [6] Leong, C. K. (2016): Credit risk scoring with Bayesian network models. Computational Economics, 47(3): 423-446.
• [7] Pavlenko, T.- Chernyak, O. (2010): Credit Risk Modeling Using Bayesian Networks. International Journal of Intelligent Systems, 25(4): 326-344.
• [8] Abramowicz, W.- Nowak, M.- Sztykiel, J. (2003): Bayesian networks as a decision support tool in credit scoring domain. In P. C. Pendharkar (Ed.), Managing data mining technologies: Techniques and applications: 1–20. Hershey: Idea Group Publications.
• [9] Shenoy, C.- Shenoy, P. P. (2000): Bayesian Network Models of Portfolio Risk and Return. The MIT Press.
• [10] De Giuli, M. E.- Maggi, M. A.- Tarantola, C. (2010): Bayesian outlier detection in capital asset pricing model. Statistical Modelling, 10(4): 375-390.
• [11] Wijayatunga, P.- Mase, S.- Nakamura, M. (2006): Appraisal of companies with Bayesian networks. International Journal of Business Intelligence and Data Mining, 1(3): 329-346.
• [12] Donaldson Soberanis, I. E. (2010): An extended Bayesian network approach for analyzing supply chain disruptions. PhD Thesis, University of Iowa.
• [13] Cattell D.- Love, P.E.D. (2013): Using Bayesian Networks to assess the risk appetite of construction contractors. 38th Australian University Building Educators Association Conference. Auckland:New Zealand.
• [14] Zuo, Y.- Kita, E. (2012): Stock price forecast using Bayesian network. Expert Systems with Applications, 39(8): 6729-6737.
• [15] Baesens, B.- Egmont-Petersen, M.- Castelo, R.- Vanthienen, J. (2002): Learning Bayesian network classifiers for credit scoring using Markov Chain Monte Carlo search. In Pattern Recognition, 2002. Proceedings. 16th International Conference on, 3:49-52. IEEE.
• [16] Gemela, J. (2001): Financial analysis using Bayesian networks. Applied Stochastic Models in Business and Industry, 17(1): 57-67.
• [17] Gemela, J. (2003): Learning Bayesian networks using various data sources and applications to financial analysis. Soft Computing, 7(5): 297-303.
• [18] Wu, Y.- McCall, J.- Corne, D. (2010): Two novels Ant Colony Optimization approaches for Bayesian network structure learning. In Evolutionary Computation (CEC), 2010 IEEE Congress on: 1-7. IEEE.
• [19] Zuo, Y.- Kita, E. (2012): Up/down analysis of stock index by using Bayesian network. Engineering Management Research, 1(2): 46.
• [20] Takci, B. B. H.- Ekinci, U. C. (2011): Bank credit risk analysis with bayesian network decision tool. International Journal Of Advanced Engineering Sciences And Technologies, 9(2): 273-279.
• [21] Weber, P.- Medina-Oliva, G.- Simon, C.- Iung, B. (2012): Overview on Bayesian networks applications for dependability, risk analysis and maintenance areas. Engineering Applications of Artificial Intelligence, 25(4): 671-682.
• [22] Olbryś J. (2009): Forecasting Portfolio Return Based on Bayesian Network Model. [in:] W.Milo, G.Szafrański, P.Wdowiński (eds.): Financial Markets. Principles of Modelling, Forecasting and Decision-Making, FindEcon Monograph Series: Advances in Financial Market Analysis, Lodz University Press, 7:157-171.
• [23] Chernyak, O., Chernyak, Y. (2011): Classification of Financial Conditions of the Enterprises in Different Industries of Ukrainian Economy Using Bayesian Networks. In HAICTA: 519-530.
• [24] Tarantola, C., Vicard, P.- Ntzoufras, I. (2012): Monitoring and improving Greek banking services using Bayesian Networks: An analysis of mystery shopping data. Expert systems with applications, 39(11): 10103-10111.
• [25] Shen, C. W. (2009): A bayesian networks approach to modeling financial risks of e-logistics investments. International journal of information technology & decision making, 8(04): 711-726.
• [26] Druzdzel, M. J. (1999): GeNIe: A development environment for graphical decision-analytic models. In Proceedings of the AMIA Symposium. American Medical Informatics Association :1206.
• [27] Pearl, J. (1988): Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, San Mateo: CA.
• [28] Heckerman, D.- Geiger, D.- Chickering, D. M. (1995): Learning Bayesian networks: The combination of knowledge and statistical data. Machine learning, 20(3): 197-243.
• [29] Jensen, F. V (1996): An introduction to Bayesian Networks, UCL Press, London.
• [30] Cowell, R. G.- Dawid, A. P.- Lauritzen, S. L.- Spiegelhalter, D. J. (1999): Probabilistic Networks and Expert Systems, Springer: New York.
• [31] Cooper, G.F.- Herskovits, E.A. (1992): A Bayesian method for the induction of probabilistic networks from data, Machine Learning, 9: 309-347.
• [32] Pearl, J.- Verma, T. S. (1995): A theory of inferred causation. In Studies in Logic and the Foundations of Mathematics, 134: 789-811. Elsevier.
• [33] Kayaalp, M.- Cooper, G. F. (2002, August): A Bayesian network scoring metric that is based on globally uniform parameter priors. In Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence, Morgan Kaufmann Publishers Inc. : 251-258.
• [34] Buntine, W. (1991): Theory refinement on Bayesian networks. In Uncertainty Proceedings 1991: 52-60.
• [35] Cheng, J.- Bell, D. A.- Liu, W. (1997): An algorithm for Bayesian belief network construction from data. In proceedings of AI & STAT’97: 83-90.
• [36] Hesar, A. S.- Tabatabaee, H.- Jalali, M. (2012): Structure learning of bayesian networks using heuristic methods. In Proc. of International Conference on Information and Knowledge Management.
• [37] Galapero, J.- Fernández, S.- Pérez, C. J.- Calle-Alonso, F.- Rey, J.- Gómez, L. (2016): Identifying risk factors for ovine respiratory processes by using Bayesian networks. Small Ruminant Research, 136: 113-120.
• [38] Dechter, R. (1992): Constraint networks. Information and Computer Science, University of California: Irvine.
• [39] Becker, A.- Geiger, D. (1996): Optimization of Pearl's method of conditioning and greedy-like approximation algorithms for the vertex feedback set problem. Artificial Intelligence, 83(1): 167-188.
• [40] Onisko, A.- Druzdzel, M. J. (2003, October): Effect of imprecision in probabilities on Bayesian network models: An empirical study. In Working notes of the European Conference on Artificial Intelligence in Medicine (AIME-03): Qualitative and Model-based Reasoning in Biomedicine. Protaras: Cyprus (October 18–22 2003).
• [41] Swets, J. A. (2014): Signal detection theory and ROC analysis in psychology and diagnostics: Collected papers. Psychology Press.