Document Type : Research Paper

Authors

Faculty of Economics, Kharazmi University, Tehran, Iran.

Abstract

This study applied a prediction-based portfolio optimization model to explore the results of portfolio predicament in the Tehran Stock Exchange. To this aim, first, the data mining approach was used to predict the petroleum products and chemical industry using clustering stock market data. Then, some effective factors, such as crude oil price, exchange rate, global interest rate, gold price, and S&P 500 index, were used to estimate each industry index using Radial Basis Function and Multi-Layer Perceptron neural networks. Finally, by comparing the validation ratios in a bullish market using K-Means, SOM, and Fuzzy C-means clustering algorithms, the best algorithm was employed to predict indicators for each industry. The sample was collected between December 15, 2008, and April 25, 2018. The results revealed that the Multi-Layer Perceptron algorithm had the highest accuracy and was the best option for portfolio predicament. However, the Fuzzy C-means algorithm produced the best clusters. Practical results showed that Sepahan oil and Kharg petrochemical stocks were the most important stocks in the short term while Kharg petrochemical, Fannavaran petrochemical, and Tehran oil refinery stocks made higher contributions in a stock portfolio in the medium- or long-term.

Keywords

Article Title [Persian]

بهینه‌سازی پرتفوی مبتنی بر پیش‌بینی برای سهام گروه‌های وابسته به نفت در ایران با استفاده از روش‌های داده کاوی

Authors [Persian]

  • محمد صیادی
  • میثم امیدی

دانشکده اقتصاد، دانشگاه خوارزمی، تهران، ایران.

Abstract [Persian]

هدف اصلی این تحقیق استفاده از یک مدل بهینه‌سازی پرتفوی مبتنی بر پیش‌بینی برای انتخاب پرتفوی سهام گروه‌های وابسته به نفت در بازار بورس تهران است. برای این منظور، ابتدا با استفاده از داده‌های خوشه‌بندی شده بازار سهام و مبتنی بر رهیافت داده‌کاوی، سهام فرآورده‌های نفتی و صنایع شیمیایی پیش‌بینی شده است. سپس، با استفاده از عوامل موثر بر تغییرات شاخص هر گروه مانند قیمت نفت خام، نرخ ارز، نرخ بهره‌ جهانی، قیمت جهانی طلا و شاخص S&P500 شاخص هر صنعت با استفاده از الگوریتم‌های شبکه عصبی MLP و RBF تخمین زده شده و در نهایت با مقایسه عملکرد هر یک از الگوریتم‌ها، بهترین الگوریتم برای پیش‌بینی رفتار شاخص هر صنعت شناسایی شده است. در ادامه با استفاده از الگوریتم‌های خوشه-بندی K-Means، SOM و FCM شرکت‌های موجود در این دوصنعت از لحاظ نسبت‌های مالی خوشه‌بندی شده و با بهترین الگوریتم سهام مناسب از هرگروه شناسایی شده است. نتایج تحقیق بیانگر آن است که الگوریتم MLP ازدقت بالاتری برخوردار است. همچنین الگوریتم FCM بهترین خوشه‌ها را تولید می‌کند. نتایج تجربی نشان می‌دهد، سهام پتروشیمی سپاهان و خارگ در کوتاه‌مدت و پتروشیمی خارگ و فناوران و پالایشگاه نفت تهران بیشترین بازده را در پرتفوی در افق میان‌مدت و بلندمدت دارد.

Keywords [Persian]

  • Stock index
  • portfolio optimization
  • data mining
  • artificial neural networks
  • clustering
Bação, F., Lobo, V., Painho, M., 2005. Self-organizing maps as substitutes for k-means clustering, International Conference on Computational Science. Springer, pp. 476-483.
Baryshevsky, D.V., 2004. The interrelation of the long-term gold yield with the yields of another asset classes. Available at SSRN 652441.
Blair, B., Poon, S.-H., Taylor, S.J., 2002. Asymmetric and crash effects in stock volatility for the S&P 100 index and its constituents. Applied Financial Economics 12, 319-329.
Bollerslev, T., 1986. Generalized autoregressive conditional heteroskedasticity. Journal of econometrics 31, 307-327.
CBI, 2018. Economic trends. Economic Statistics Department, Tehran, Iran.
Chen, A.-S., Leung, M.T., 2004. Regression neural network for error correction in foreign exchange forecasting and trading. Computers & Operations Research 31, 1049-1068.
Chen, G., Jaradat, S.A., Banerjee, N., Tanaka, T.S., Ko, M.S., Zhang, M.Q., 2002. Evaluation and comparison of clustering algorithms in analyzing ES cell gene expression data. Statistica Sinica, 241-262.
Chiang, W.-C., Urban, T.L., Baldridge, G.W., 1996. A neural network approach to mutual fund net asset value forecasting. Omega 24, 205-215.
Chiu, C.-Y., Chen, Y.-F., Kuo, I.-T., Ku, H.C., 2009. An intelligent market segmentation system using k-means and particle swarm optimization. Expert Systems with Applications 36, 4558-4565.
Durante, F., Foscolo, E., 2013. An analysis of the dependence among financial markets by spatial contagion. International Journal of Intelligent Systems 28, 319-331.
FRED, F.R.E.D., 2018. Federal Reserve Bank of St. Louis: Exchange Rates. Available online at http://research. stlouisfed. org/fred2/categories/158. Last accessed 5.
Galeshchuk, S., 2016. Neural networks performance in exchange rate prediction. Neurocomputing 172, 446-452.
Gandhmal, D.P., Kumar, K., 2019. Systematic analysis and review of stock market prediction techniques. Computer Science Review 34, 100190.
Hamerly, G., Elkan, C., 2002. Alternatives to the k-means algorithm that find better clusterings, Proceedings of the eleventh international conference on Information and knowledge management. ACM, pp. 600-607.
Huang, C.-F., 2012. A hybrid stock selection model using genetic algorithms and support vector regression. Applied Soft Computing 12, 807-818.
Kanjamapornkul, K., Pinčák, R., Bartoš, E., 2016. The study of Thai stock market across the 2008 financial crisis. Physica A: Statistical Mechanics and its Applications 462, 117-133.
Kasturi, J., Acharya, R., Ramanathan, M., 2003. An information theoretic approach for analyzing temporal patterns of gene expression. Bioinformatics 19, 449-458.
Li, H., 2019. Multivariate time series clustering based on common principal component analysis. Neurocomputing 349, 239-247.
Liao, S.-H., Chou, S.-Y., 2013. Data mining investigation of co-movements on the Taiwan and China stock markets for future investment portfolio. Expert Systems with Applications 40, 1542-1554.
Lu, Y.-N., Li, S.-P., Zhong, L.-X., Jiang, X.-F., Ren, F., 2018. A clustering-based portfolio strategy incorporating momentum effect and market trend prediction. Chaos, Solitons & Fractals 117, 1-15.
Mashayekh, S., Moradkhani, H.H., Jafari, M., 2011. Impact of macroeconomic variables on stock market: The case of Iran, 2nd International Conference on Business and Economic Research (2nd ICBER 2011) Proceeding. Conference Master Resources, pp. 350-360.
Miao, K., Chen, F., Zhao, Z., 2007. Stock price forecast based on bacterial colony RBF neural network [j]. Journal of Qingdao University (Natural Science Edition) 2.
Misiunas, N., Oztekin, A., Chen, Y., Chandra, K., 2016. DEANN: A healthcare analytic methodology of data envelopment analysis and artificial neural networks for the prediction of organ recipient functional status. Omega 58, 46-54.
Momeni, M., Mohseni, M., Soofi, M., 2015. Clustering Stock Market Companies via K-Means Algorithm. Kuwait Chapter of the Arabian Journal of Business and Management Review 4, 1.
Nair, B.B., Kumar, P.S., Sakthivel, N., Vipin, U., 2017. Clustering stock price time series data to generate stock trading recommendations: An empirical study. Expert Systems with Applications 70, 20-36.
Nanda, S., Mahanty, B., Tiwari, M., 2010. Clustering Indian stock market data for portfolio management. Expert Systems with Applications 37, 8793-8798.
Patel, J., Shah, S., Thakkar, P., Kotecha, K., 2015. Predicting stock market index using fusion of machine learning techniques. Expert Systems with Applications 42, 2162-2172.
Rapach, D.E., Wohar, M.E., Rangvid, J., 2005. Macro variables and international stock return predictability. International journal of forecasting 21, 137-166.
Rezaee, M.J., Jozmaleki, M., Valipour, M., 2018. Integrating dynamic fuzzy C-means, data envelopment analysis and artificial neural network to online prediction performance of companies in stock exchange. Physica A: Statistical Mechanics and its Applications 489, 78-93.
Santos, A.A.P., da Costa Jr, N.C.A., dos Santos Coelho, L., 2007. Computational intelligence approaches and linear models in case studies of forecasting exchange rates. Expert Systems with Applications 33, 816-823.
Schwartz, R.A., Whitcomb, D.K., 1977. Evidence on the presence and causes of serial correlation in market model residuals. Journal of Financial and Quantitative Analysis 12, 291-313.
Shu, G., Zeng, B., Chen, Y.P., Smith, O.H., 2003. Performance assessment of kernel density clustering for gene expression profile data. International Journal of Genomics 4, 287-299.
Statistic, I.a., 2018. Information and Statistic, in: Ministry of Industry, M.a.T.o.I.R.o.I. (Ed.).
Tibshirani, R., Walther, G., Hastie, T., 2001. Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 63, 411-423.
TSE, 2018. Tehran Stock Exchange. Tehran Stock Exchange Corp, Tehran, Iran.
Venkatesan, P., Anitha, S., 2006. Application of a radial basis function neural network for diagnosis of diabetes mellitus. Current Science 91, 1195-1199.
Yilmaz, I., Kaynar, O., 2011. Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils. Expert systems with applications 38, 5958-5966.
Zhang, C., Almpanidis, G., Wang, W., Liu, C., 2018. An empirical evaluation of high utility itemset mining algorithms. Expert Systems with Applications 101, 91-115.
Zhang, Y., Wu, L., 2009. Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network. Expert systems with applications 36, 8849-8854.
Zhong, X., 2004. A study of several statistical methods for classification with application to microbial source tracking. Worcester Polytechnic Institute.
Zhong, X., Enke, D., 2017. A comprehensive cluster and classification mining procedure for daily stock market return forecasting. Neurocomputing 267, 152-168.
Zhong, X., Ma, S.P., Yu, R.Z., Zhang, B., 2001. Data mining: A survey. PRAI 14.