تحلیل متنی خبرهای بانک مرکزی در پیش‌بینی بلندمدت شاخص بورس اوراق بهادار تهران
محورهای موضوعی : عمومىمیثم هاشمی 1 , مهران رضایی 2 * , مرجان کائدی 3
1 - مهندسی کامپیوتر، دانشگاه اصفهان
2 - عضو هیات علمی
3 - دانشکده مهندسی کامپیوتر، دانشگاه اصفهان
کلید واژه: شاخص کل بورس تهران, پیش‌بینی بلندمدت, تحلیل متنی, اخبار مالی, وزن‌دهی DF,
چکیده مقاله :
بازارهای مالی همواره تحت تاثیر انتشارات رسانه‌های خبری بوده‌اند. به همین دلیل تحلیل اسناد خبری به عنوان یک رهیافت برای پیش‌بینی بورس اوراق بهادار به کار رفته است. در تحقیقات پیشین در این زمینه، تحلیل اسناد متنی با استفاده از روش‌های رایج در بازیابی اطلاعات انجام گرفته است. مبنای آماری این روش‌های رایج بر این است که کلماتی که در مجموعه اسناد کم‌تکرار هستند ولی در یک سند پرتکرار هستند، نسبت به کلمات پرتکرار مجموعه و سند، وزن بالاتری بگیرند. ولی مشکل این است که برخلاف آنچه در تحقیقات قبلی در نظر گرفته شده است، در اسناد خبری، کلمات پرتکرار نشان‌دهنده خبرهای مهم و تاثیرگذار هستند. در این تحقیق برای رفع این مشکل، یک روش جدید برای وزن‌دهی کلمات اسناد خبری ارائه شده است. روش پیشنهادی روی داده‌های شاخص کل بورس اوراق بهادار تهران و اسناد خبری بانک مرکزی ایران در بازه زمانی 1384 تا 1399 ارزیابی شده است. نتایج حاکی از 64 درصد صعودی و 41 درصد نزولی دقت پیش‌بینی نوسانات شاخص کل و کاهش 10 درصد میانگین درصد خطای مطلق نسبت به بهترین روش رایج می‌باشد. همچنین نتایج نشان می‌دهد که اگرچه تغییرات در نسبت بین تعداد کلمات مثبت و منفی شواهد پیش گویانه ای ارائه نمیکند اما بین خبرهای منتشرشده از سوی بانک مرکزی و نوسانات شاخص کل بورس تهران ارتباط وجود دارد.
Financial markets have always been under influence of media news; therefore, text analysis of news is considered as an effective method of stock exchange forecasting. Research in this context has been conducted with the help of information retrieval techniques, in which high frequency words in a document that appeared sporadically in the whole corpus received higher weight than others. In contrast, the words which appeared in many news of a corpus, during a certain time, indicate the importance of an event. In our research, to address this contradiction, a new technique of assigning weight to influential words of news is presented. Financial news of Iran Central Bank (CBI) and actual data of Tehran Stock Exchange Index (TSEI) in the duration of 2005 to 2020 AD were utilized to evaluate the proposed method. The empirical results show 64% and 41% accuracy of trend prediction when TSEI moves upward and downward respectively and about 10% decreasing in Mean Absolute Error (MAE) to compare with prevalent techniques. While, the changes of the ratio between the number of positive and negative words in news does not offer predictive or analytical evidences, our results show that, there still exists a meaningful relationship between CBI news and TSEI fluctuations.
[1] R. P. Schumaker and H. Chen, “Textual analysis of stock market prediction using breaking financial news: The AZFin text system,” ACM Transactions on Information Systems (TOIS), vol. 27, p. 12, 2009.
[2] A. Kloptchenko, T. Eklund, J. Karlsson, B. Back, H. Vanharanta, and A. Visa, “Combining data and text mining techniques for analysing financial reports,” Intelligent systems in accounting, finance and management, vol. 12, pp. 29-41, 2004.
[3] C. Robertson, S. Geva, and R. C. Wolff, “Can the Content of Public News be used to Forecast Abnormal Stock Market Behaviour?,” in Seventh IEEE International Conference on Data Mining, ICDM 2007, pp. 637-642.
[4] E. F. Fama, “The behavior of stock-market prices,” The journal of Business, vol. 38, pp. 34-105, 1965.
[5] S. Chopra and P. Meindl, Supply Chain Managemnt Strategy, planning and operation. 3rd Edition, Pearson Prentice Hall, ISBN: 0-13-208608-5, 2007.
[6] P. Falinouss, “Stock trend prediction using news articles: a text mining approach,” M.S. thesis, Lulea university of thechnology, Lulea, Sweden, 2007.
[7] K. G. Aase, “Text Mining of News Articles for Stock Price Predictions,” M.S. thesis, Norwegian University of Science and Technology, Trondheim, Norway, 2011.
[8] M. Arias, A. Arratia, and R. Xuriguera, “Forecasting with Twitter Data,” ACM Transactions on Intelligent Systems Technology, 5, 1, Article 8 (January 2014), 24 pages.
[9] M. A. Mittermayer, “Forecasting intraday stock price trends with text mining techniques,” in Proceedings of the 37th Annual Hawaii International Conference on System Sciences, Big Island, 0-7695-2056-1, IEEE, 5-8 Jan, 2004.
[10] M. Butler and V. Kešelj, “Financial Forecasting Using Character N-Gram Analysis and Readability Scores of Annual Reports,” In Advances in Artificial Intelligence (pp. 39-51). Springer Berlin Heidelberg, 2009.
[11] B. G. Malkiel, “A Random Walk Down Wall Street: The Time-Tested Strategy for Successful Investing,” WW Norton & Company, New York, 1973.
[12] C. Robertson, S. Geva, and R. C. Wolff, “Can the Content of Public News be used to Forecast Abnormal Stock Market Behaviour?,” in Seventh IEEE International Conference on Data Mining, ICDM 2007, pp. 637-642.
[13] S. Bacher and H. Stuckenschmidt, “Mining Unstructured Financial News to Forecast Intraday Stock Price Movements,” M.S. thesis, University of Mannheim, Mannheim, Germany, Oct, 2012.
[14] Kartick Gupta, Rajabrata Banerjee, “Does OPEC news sentiment influence stock returns of energy firms in the United States?” Energy Economics, vol. 77, pp. 34–45, 2019.
[15] George Guan-Ru Wu, Tony Chieh-Tse Hou, Jin-Lung Lin, “Can economic news predict Taiwan stock market returns?”, Asia Pacific Management Review, vol. 24, pp. 54-59, 2019.
[16] Yu-Chen Wei, Yang-Cheng Lu, Jen-Nan Chen, Yen-Ju Hsu, “Informativeness of the market news sentiment in the Taiwan stock market”, North American Journal of Economics and Finance, vol. 39, PP. 158-181, 2017.
[17] S. Feuerriegel, J. Gordon, “Long-term stock index forecasting based on text mining of regulatory disclosures,” Decision Support Systems, vol. 112, pp. 88-97, 2018.
[18] R. Ren, D. D. Wu, and T. Liu, “Forecasting stock market movement direction using sentiment analysis and support vector machine,” IEEE Systems Journal, vol. 13, no. 1, pp. 760-770, 2019.
[19] A.S. Ab. Rahman, S. Abdul-Rahman, and S. Mutalib, “Mining textual terms for stock market prediction analysis using financial news,”in Mohamed A., Berry M., Yap B. (eds) Soft Computing in Data Science. SCDS 2017. Communications in Computer and Information Science, vol. 788. Springer, Singapore, 2017.
[20] H. Naderi Semiromi, S. Lessmann, and Wiebke Peters, "News will tell: Forecasting foreign exchange rates based on news story events in the economy calendar,” The North American Journal of Economics and Finance vol. 52, 101-181, 2020.
[21] L. Yu, S. Wang, and K. Lai, “A rough-set-refined text mining approach for crude oil market tendency forecasting,” International Journal of Knowledge and Systems Sciences, vol. 2, pp. 33-46, 2005.
[22] R. Luss and A. d'Aspremont, “Predicting abnormal returns from news using text classification,” Quantitative Finance, arXiv:0809.2792v3, 2009.
[23] M. V. Pinto and K. Asnani, “Stock Price Prediction Using Quotes and Financial News,” International Journal of Soft Computing, vol. 1, Issue 5, November 2011.
[24] M. R. Amin-Naseri and E. A. Gharacheh, “A hybrid artificial intelligence approach to monthly forecasting of crude oil price time series,” in The
Proceedings of the 10th International Conference on Engineering Applications of Neural Networks, CEUR-WS284, 2007, pp. 160-167. [25] W. Antweiler and M. Z. Frank, “Is all that talk just noise? The information content of internet stock message boards,” The Journal of Finance, vol. 59, pp. 1259-1294, 2004.
[26] E. Guardia-Sebaoun, A. Rafrafi, V. Guigue, and P. Gallinari, “Cross-media sentiment classification and application to box-office forecasting,” in Proceedings of the 10th Conference on Open Research Areas in Information Retrieval, 2013, pp. 201-208.
[27] X. Guo-Xiang, S. Ben-Chang, H. Yen-Bin, S. Po-Chih, and C. Kuo-Hao, “To Integrate Text Mining and Artificial Neural Network to Forecast Gold Futures Price,” in International Conference on New Trends in Information and Service Science, NISS'09, 2009, pp. 1014-1020.
[28] S. Asur and B. A. Huberman, “Predicting the future with social media,” In International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), 2010 IEEE/WIC/ACM (Vol. 1, pp. 492-499). IEEE.
[29] Stefan Feuerriegel, Julius Gordon, “News-based forecasts of macroeconomic indicators: A semantic path model for interpretable predictions”, EuropeanJournal of Operational Research, vol. 272, pp. 162–175, 2019.
[30] Weiling Chen, Chai Kiat Yeo, Chiew Tong Lau, Bu Sung Lee, “Leveraging social media news to predict stock index movement using RNN-boost”, Data & Knowledge Engineering, vol. 118, pp. 14-24, 2018.
[31] KiHwan Nam, NohY oon Seong, “Financial news-based stock movement prediction using causality analysis of influence in the Korean stock market”, Decision Support Systems, Decision Support Systems, vol. 117, pp. 100-112, 2019.
[32] W. B. Yu, B. R. Lea, and B. Guruswamy, “A Theoretic Framework Integrating Text Mining and Energy Demand Forecasting,” IJEBM, vol. 5, pp. 211-224, 2007.
[33] R. Baeza-Yates and B. Ribeiro-Neto, Modern information retrieval. Vol. 463. New York: ACM press, 1999.
[34] D. Thorleuchter and D. Van den Poel, “Predicting e-commerce company success by mining the text of its publicly-accessible website,” Expert Systems with Applications, vol. 39, pp. 13026-13034, 2012.
[35] S. Mahfoud and G. Mani, Financial forecasting using genetic algorithms. Applied Artificial Intelligence, vol. 10, no. 6, 543-566, 1996.
[36] Tehran Stock Exchange, Available: http://www.tse.ir/market/Indices.aspx
[37] Cambridge University Press. Available: http://nlp.stanford.edu/IR-book/html/htmledition/tokenization-1.html
[38] Cambridge University Press. Available: http://nlp.stanford.edu/IR-book/html/htmledition/dropping-common-terms-stop-words-1.html
[39] X. Liang and R. C. Chen, “Mining Stock News in Cyberworid Based on Natural Language Processing and Neural Networks,” in International Conference on Neural Networks and Brain, 2005, ICNN&B'05. Vol. 2, IEEE.
[40] G. Salton, A. Wong, and C. S. Yang, “A vector space model for automatic indexing,” Communications of the ACM 18.11 (1975): 613-620.
[41] B. Drury, “A Text Mining System for Evaluating the Stock Market,” Ph.D. Dissertation, Universities of Minho, Aveiro and Porto, 2009.
[42] رضا راعي، علي نیک عهد قصیرائي و مصطفي حبیبي، «پیش بیني شاخص بورس اوراق بهادار تهران با تركیب روشهاي آنالیز مولفه‌هاي اصلي، رگرسیون بردارپشتیبان و حركت تجمعي ذرات،» راهبرد مديريت مالي، سال چهارم، ماه پانزدهم، 1395، صص: 1-23.
]43[ امیردایی، امیدعبادتی و کیوان برنا، «به‌کارگیری وب‌کاوی در پیش‌بینی جهت قیمت سهام گروه محصولات شیمیایی در بورس اوراق بهادار»، فصل‌نامه علمی- پژوهشی فناوری اطلاعات و ارتباطات ایران، سال یازدهم، شماره‌های 39 و 40، بهار و تابستان 1398، صص: 19 – 48.