نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار دانشکده مدیریت دانشگاه تهران

2 کارشناس ارشد مدیریت مالی دانشگاه تهران

چکیده

عدم تطابق رفتار واقعی بازارهای مالی با آنچه تئوری‌های اقتصادی تحت عنوان بازارهای کارا ارائه نموده‌اند، سبب ظهور حوزه‌های مطالعاتی جدیدی مانند اقتصاد و مالی رفتاری (ترکیب اقتصاد و علوم رفتاری) و یا فیزیک اقتصاد شده است تا شاید بتوان از این طریق پاسخ‌های مناسب‌تری به جهت تبیین رفتار بازارهای مالی ارائه داد. هدف مقاله، بررسی امکان کاهش ریسک سبد دارایی‌ها از طریق بکارگیری تئوری ماتریس‌های تصادفی برای شناسایی اطلاعات نوفه‌ای ماتریس کواریانس سهام و تشکیل سبد بهینه دارایی‌ها با استفاده از اطلاعات نوفه‌زدایی ‌شده می‌باشد.
ماتریس کواریانس نوفه‌زدایی شده، تبیین­کنندة اطلاعات پایدارتر و با قابلیت اتکاء بیشتری از ارتباط موجود بین رفتار سهام می‌باشد. در پژوهش حاضراطلاعات 70 شرکت پر معامله در بورس اوراق بهادار تهران طی فروردین83 تا خرداد87 (شامل 1020 روز معاملاتی) مورد بررسی قرار گرفته‌اند. نتایج تحقیق نشان می‌دهد، پرتفولیوهای بهینه‌ای که با استفاده از اطلاعات نوفه‌زدایی شده بدست آمده‌اند نسبت به پرتفولیوهای بهینة مبتنی بر اطلاعات تجربی (اطلاعات نوفه‌دار)، به طور معنی‌داری ریسک کمتری دارند و استفاده از تئوری ماتریس‌های رندومی در مدیریت ریسک در بورس اوراق بهادار تهران مفید و مؤثر می‌باشد. توجه به این مسئله به فعالان بازار و مدیران پرتفولیو پیشنهاد می‌گردد.

کلیدواژه‌ها

عنوان مقاله [English]

Portfolio Optimization by Using Denoised Covariance Matrix in Tehran Stock Exchange

نویسندگان [English]

  • Shapour Mohammadi, 1
  • Mohamad Ali Khojasteh 2

1 Assistant Professor, School of Management, University of Tehran

2 Master of Financial Management, University of Tehran

چکیده [English]

Deviation of financial markets behavior in reality from which the Efficient Market Hypothesis suggests is a serious challenge. This fact is led to emerging of new fields in economics, like behavioral economics/finance and recently Econophysics/finance. These new fields aim to provide new ways of thinking about financial time series as the result of human factors and idealized rationality. They may shed some light on the inner workings of the market. In this study, we want to improve optimizing portfolio selection through denoising the empirical covariance matrix by using Random Matrix Theory.
We extract stable relations of stocks from empirical covariance matrix and compare the results of optimized portfolios in noisy and denoised states.
We use daily returns of 70 stocks of Tehran Stock Exchange from March-2004 to May-2008. We show that denoised data significantly reduces the real risk of optimized portfolios and is beneficial for risk management and we recommend it to portfolio managers and financial analysts in real market.

کلیدواژه‌ها [English]

  • Portfolio Optimization
  • Noise
  • Denoising
  • Stocks Covariance Matrix
  • Risk Management
  • Random Matrix Theory

منابع

1-          Bandi, Federico M., Russell, Jeffrey R., "Separating microstructure noise from volatility", Journal of Financial Economics, No.79, 2006, pp.655-692.

2-          Berkman, Henk, Koch, Paul D, "Noise trading and the price formation process", Journal of Empirical Finance, No.15, 2008, pp.232-250.

3-          Black, Fischer, "Noise", Journal of Finance, No.41, 1986, pp.529-543.

4-          Bouchaud J. P., Laloux L., Miceli M.A., Potters M., "Large dimension forecasting models and random singular value spectra", Eur. Phys. J. B, Vol.55, 2007, pp.201-207.

5-           Bouchaud J.P., Potter M, "Theory of Financial Risks, From statistical physics to risk management", Cambridge University Press, Cambridge, United Kingdom, 2000.

6-                     Burda Z., Gorlich A., Jarosz A., Jurkiewicz J, "Signal and noise in correlation matrix", Physica A, Statistical Mechanics and its Applications, Vol.343, No.15, 2004,pp.295-310.

7-          Burda Z., Jurkiewicz J., Nowak M. A., Papp G. Z, "Levy matrices and financial covariances", Acta Physica Polonica, Series B, Vol.34, No.10, 2003, pp.4747-4763.

8-          Campbell, John Y., Kyle, Albert S, "Smart money, noise trading and stock price behavior", The review of economic studies, Vol.60, No.1, 1993,pp.1-34.

9-          Chelley-Steeley, Patricia, "The trading mechanism, cross listed stocks:a comparison of the Paris Bourse and SEAQ International", Int. Fin. Markets, No.13, 2003, pp.401-417.

10-       Cukur, Sadik, Eryigit, Mehmet, Eryigit, Resul, "Cross correlations in an emerging market financial data", Physica A, Statistical Mechanics and its Applications, Vol.376, 2007, pp.555-564.

11-       Daly J., Cranea M., Ruskin H.J., "Random matrix theory filters in portfolio optimization: A stability and risk assessment", Physica A, Statistical Mechanics and its Applications, Vol.387, No.16-17, 2008, pp.4248-4260.

12-       De Long, J.B., Shleifer, A., Summers, L.H., Waldman, R.J, "Noise trader risk in financial markets", Journal of Political Economy, No.98,1990 ,pp.703-738.

13-        De Long, J.B., Shleifer, A., Summers, L.H., Waldmann, R.J, "The Survival of Noise Traders in Financial Markets", Journal of Business, No.64, 1991, pp.1-19.

14-       Drozdz S., Grummer F., Gorski A. Z., Ruf F., Speth J, "Dynamics of competition between collectivity and noise in the stock market", Physica A, Statistical Mechanics and its Applications, Vol.287, No.3-4, 2000, pp.440-449.

15-       Drozdz S., Grummer F., Ruf F., Speth J, "Towards identifying the world stock market cross-correlations: DAX versus Dow Jones", Physica A, Statistical Mechanics and its Applications, Vol.294, No.1-2, 2001, pp.226-234.

16-       Jung, W., Chae S., Yang J., Moon H, "Characteristics of the Korean stock market correlations", Physica A, Statistical Mechanics and its Applications, Vol.361, No.1, 2006, pp.263-271.

17-       Kelly, Morgan, "Do Noise Traders Influence Stock Prices?", Journal of Money, Credit and Banking, Vol.29, 1997, pp.351-363.

18-       Kulkarni, Varsha and Deo, Nivedita, "Correlation and volatility in an Indian stock market: A random matrix approach", The European Physical Journal B, Condensed Matter and Complex Systems, Springer Berlin, Heidelberg, Vol.60, No.1, 2007, pp.101-109.

19-       Kurov, Alexander, "Information and Noise in Financial Markets: Evidence from the E-mini Index Futures", College of Business and Economics, West Virginia University, http://ssrn.com/abstract=1086021.

20-        Laloux L., Cizeau P., Bouchaud J.P., Potters M., "Noise Dressing in Financial Correlation Matrices", Physical Review Letters, Vol.83, No.7, 1999,pp.1467-1470.

21-       Malevergne Y., Sornette D, "Collective origin of the coexistence of apparent random matrix theory noise and of factors in large sample correlation matrices", Physica A, Vol.331, No.3-4, 2004, pp.660-668.

22-       Markowitz H, "Portfolio Selection", Journal of finance, Vol.7, 1952, p.91.

23-        Martins Andre C.R, "Non-stationary correlation matrices and noise", Physica A, Statistical Mechanics and its Applications, Vol.379, No.2, 2007, pp.552-558.

24-       Maslov, Sergei, "Measures of globalization based on cross-correlations of world financial indices", Physica A, Statistical Mechanics and its Applications, Vol.301, No.1-4,2001 , pp.397-406

25-       Mehta M. L, "Random matrices and the statistical theory of energy levels", Academic press Inc., New York, 1967.

26-       Pafka S., Kondor I, "Noisy covariance matrices and portfolio optimization", Eur. Phys. J. B, Vol.27, No.2, 2002, pp.277-80.

27-       Pafka S., Kondor I, "Noisy covariance matrices and portfolio optimization. II", Physica A, Vol.319, 2003, pp.487-494.

28-        Pafka S., Kondor I, "Estimated correlation matrices and portfolio optimization", Physica A, Statistical Mechanics and its Applications , Vol.343, 2004, pp.623-634.

29-        Papp G., Pafkaa Sz., Nowakc M.A., Kondor I, "Random matrix filtering in portfolio optimization", Acta Physica Polonica B, Vol.36, No.9,2005, pp.2757-2765.

30-       Plerou V., Gopikrishnan P., Rosenow B., Amaral L., Stanley H.E, "Universal and Non-universal Properties of Cross Correlations in Financial Time Series", Physical Review Letters, Vol.83, No.7, 1999, pp.1471-1474

31-       Plerou V., Gopikrishnan P., Rosenow B., Amaral L. and Stanley H.E., "A random matrix theory approach to financial cross-correlations", Physica A, Vol.287, 2000, pp.374-382.

32-       Plerou V., Gopikrishnan P., Rosenow B., Amaral L.A.N., Stanley H.E., "Collective behavior of stock price movements A random matrix theory approach", Physica A, Vol.299, No.1-2, 2001, pp.175-180.

33-       Scruggs, John T, "Noise trader risk: Evidence from the Siamese twins", Journal of Financial Markets, No.10, 2007, pp.76-105.

34-       Sengupta A.M., Mitra P.P, "Distributions of Singular Values for Some Random Matrices", Phys. Rev. E, Vol.60, 1999, pp.3389-3392.

35-       Shleifer, A., Summers, L.H, "The Noise Trader Approach to Finance",  Journal of Economic Perspectives, No.4, 1990, pp.19-33.

36-                Siriopoulos, Costas, Leontitsis, Alexandros, "Nonlinear Noise Estimation in International Capital Markets", Multinational Finance Journal, vol.6, No.1, 2002, pp.43-63.

37-       Trueman, Brett, "A Theory of Noise Trading in Securities Markets", The Journal of finance, Vol.43, No.1, 1988, pp.83-95. 

38-        Utsugi, Akihiko, Ino, Kazusumi, Oshikawa, Masaki, "Random matrix theory analysis of cross correlations in financial markets", Phys. Rev. E 70, 026110, 2004.

39-       Verma, Rahul, Verma, Priti, "Noise trading and stock market volatility", J. of Multi. Fin. Manag., No.17, 2007, pp.231-243.

40-       Vuorenmaa, Tommi A, (2008). "Decimalization, Realized Volatility, and Market Microstructure Noise", University of Helsinki, FINLAND, MPRA Paper No. 8692, http://mpra.ub.uni-muenchen.de/8692/ ISSN 17950562.

41-       Wigner, E.P,."On a Class of Analytic Functions from the Quantum Theory of Collisions", Annals of Mathematics, Vol.53, No.1, 1951, pp.36-67.

42-       Wilcox D., Gebbie T, "On the analysis of cross-correlations in South African market data", Physica A, 2004, pp.294-298.

43-        Yang Hu, Shing, "A simple estimate of noise and its determinant in a call auction market", International Review of Financial Analysis, No.15, 2006, pp.348-362.