TIME SERIES ANALYSIS ON STOCK MARKET FOR TEXT MINING CORRELATION OF ECONOMY NEWS

Öz

This paper proposes an information retrieval method for the economy news. The effect of economy news, are researched in the word level and stock market values are considered as the ground proof. The correlation between stock market prices and economy news is an already addressed problem for most of the countries. The most well-known approach is applying the text mining approaches to the news and some time series analysis techniques over stock market closing values in order to apply classification or cluster- ing algorithms over the features extracted. This study goes further and tries to ask the question what are the available time series analysis techniques for the stock market closing values and which one is the most suitable? In this study, the news and their dates are collected into a database and text mining is applied over the news, the text mining part has been kept simple with only term frequency – in- verse document frequency method. For the time series analysis part, we have studied 10 different methods such as random walk, moving average, acceleration, Bollinger band, price rate of change, periodic average, difference, momentum or relative strength index and their variation. In this study we have also explained these techniques in a comparative way and we have applied the methods over Turkish Stock Market closing values for more than a 2 year period. On the other hand, we have applied the term frequency – inverse document frequency method on the economy news of one of the high-circulating newspapers in Turkey

Anahtar Kelimeler

• Data Mining, Time Series Analysis, Big Data, Stock Market Analysis, Bollinger band, RSI index, Moving Average, Momentum, Random Walk, Text Mining, Signal Processing

Kaynakça

1. AsiaPac Finance (2013), List of Technical Analysis Trading Indicators for Stocks and Forex, http://www.asiapacfinance.com/ trading-strategies/technicalindicators Accessed February 2013].
2. Braun, Helmut and John S Chandler (1987),"Predicting stock market behavior through rule induction: an application of the learning-fromexample approach."
3. Decision Sciences 18, No. 3,pp. 415-429. Fung, Gabriel P. C, Jeffrey X Yu and Wai Lam (2002), "News sensitive stock trend prediction." Lecture Notes in Computer Science (Springer-Verlag London, UK) ,Vo. 233, pp. 481– 493.
4. Halgamuge, Saman, Y Zhai and Arthur Hsu (2007), "Combining News and Technical Indicators in Daily Stock Price Trends Prediction." Advances in Neural
5. Networks - ISNN 2007 (Lecture Notes in Computer Science). Springer-Verlag Heidelberg, pp. 1087-1096.
6. Hecht, Nielsen Robert (1987),"Kolmogorov’s mapping neural network existence theorem." IEEE First Annual International Conference on Neural Networks. San Diego, USA,pp. 11-14.
7. Karaman, Abdullah S. and Tayfur Altiok (2004), "An experimental study on forecast-ing using TES processes." WSC’04, Proceedings of the 36th conference on Winter simulation,pp. 437-442.
8. Keikha, Mostafa, Mark James Carman and Fabio Crestani (2009), "Blog distillation using random walks." SIGIR’09, Proceedings of the 32nd international

9. ACM SIGIR conference on Research and devel-opment in information retrieval,pp. 639-639. Lu, Hsin-Min, Nina WanHsin Huang, Zhu Zhang and Tsai-Jyh Chen (2009),
10. "Identifying Firm-Specific Risk Statements in News Articles." PAISI '09 Proceedings of the Pacific Asia Workshop on Intelligence and Security Informatics. Springer-Verlag Berlin, Heidelberg,pp. 42-53. Mahajan, Anuj, Lipika Dey and Sk Mirajul Haque (2008), "Mining Financial
11. News for Major Events and Their Impacts on the Market." Web Intelligence and Intelligent Agent Technology, 2008. WI-IAT '08. IEEE/WIC/ACM International Conference on,pp. 423-426.
12. Mahmoud, Safaa, and Moumen T. El-Melegy (2004), "Evaluation of diversity measures for multiple classifier fusion by majority voting." Electrical, Electronic and Computer Engineering, 2004. ICEEC '04. 2004 International Conference on,pp. 169- 172.
13. Masud, Mohammad M, et al. (2011),"Detecting Recurring and Novel Classes in
14. Concept-Drifting Data Streams." ICDM '11 Proceedings of the 2011 IEEE 11th
15. International Conference on Data Mining. Washington, DC, USA: IEEE Computer Society, pp. 1176-1181.
16. Mitchell, Tom M (1997), Machine learning. New York: McGraw Hill.
17. Mittermayer, Marc-André (2004) "Forecasting intraday stock price trends with text mining techniques." HICSS '04 Proceedings of the Proceedings of the 37th
18. Annual Hawaii International Conference on System Sciences (HICSS'04). IEEE Computer Society Washington, DC, USA, pp. 64-73. Mittermayer, Marc-André and Gerhard F Knolmayer (2006), "NewsCATS: A
19. News Categorization and Trading System." ICDM '06: Proceedings of the Sixth International Conference on Data Mining. IEEE Computer Society, pp. 1002
20. Nikfarjam, Azadeh, Ehsan Emadzadeh and Saravanan Muthaiyah (2010), "Text mining approaches for stock market prediction." Computer and Automation
21. Engineering (ICCAE), 2010 The 2nd International Conference on,pp. 256- 260.
22. Ocak, Ibrahim and Seker, Sadi Evren (2012), "Estimation of Elastic Modulus of
23. Intact Rocks by Artificial Neural Network", Rock Mechanics and Rock Engineering (RMRE), Vol. 45, issue 6, pp. 1047-1054
24. Ocak, Ibrahim and Seker, Sadi Evren (2013), "Calculation of Surface Settlements caused by EPBM tunneling using artificial neural network, SVM and Gaussian
25. Processes", Vol 70, issue 3, pp. 1263-1276
26. Rachlin, Gil, Mark Last, Dima Alberg and Abraham Kandel (2007), "ADMIRAL:
27. A Data Mining Based Financial Trading System." Computational Intelligence and Data Mining, 2007. CIDM 2007. IEEE Symposium on. doi: 1109/CIDM.2007.368947, pp. 720 - 725.
28. Rosenblatt, Frank (1962), "Principles of neurodynamics: perceptrons and the theory of brain mechanisms." Washington: Spartan Books.
29. Schalkoff, R J (1997), Artificial neural network. New York: McGraw Hill.
30. Schumaker, Robert P. and Hsinchun Chen (2009), "Textual analysis of stock market prediction using breaking financial news:The AZFin Text system." ACM
31. Transactions on Information Systems (TOIS) (ACM New York, NY, USA ) ,Vol. , No. 2,pp. 1-19. Seker, Sadi Evren and Diri, Banu (2010) "TimeML and Turkish Temporal Logic",
32. International Conference on Artificial Intelligence (ICAI10), vol. 10, pp. 881-887
33. Sadi Evren SEKER, Cihan Mert, Khaled Al-Naami, Ugur Ayan, Nuri Ozalp, "Ensemble Classification over Stock Market Time Series and Economy News", IEEE Conference on Intelligence and Security Informatics, (ISI2013), pp. 272
34. Soni, Ankit, Van Eck, Nees Jan and Kaymak Uzay (2007), "Prediction of stock price movements based on concept map information." IEEE Symposium on
35. Computational Intelligence in Multicriteria Decision Making. Honolulu, HI, pp. 211. Tan, Fook Hwa (n.d.), "Interpreting News Flashes for Automatic Stock Price Movement Prediction." Erasmus University Rotterdam. Trappe, Wade and Lawrence C. Washington (2006), Introduction to
36. Cryptography with Coding Theory. Pearson Prentice Hall. Wasserman, Philip D. and Tom Schwartz (1988), "Neural networks II. What are they and why is everybody so interested in them now?" IEEE Expert 3, No. 1,pp. 15.
37. Wilder, J. Welles (1978), New Concepts in Technical Trading Systems.
38. Wuthrich, B, V Cho, S Leung, D Permunetilleke, K Sankaran and J Zhang (1998),
39. "Daily stock market forecast from textual web data." SMC98 Conference Proceedings 1998 IEEE International Conference on Systems Man and Cybernetics Cat No98CH36218. Ieee, pp. 2720-2725.
40. Yahia, Moawia Elfaki and B. A Ibrahim (2003), "K-nearest neighbor and C4.5 algorithms as data mining methods: advantages and difficulties." Computer
41. Systems and Applications, 2003. Book of Abstracts. ACS/IEEE International
42. Conference on. Tunis, Tunisia, pp. 103.