A Prediction of Attractive Evaluation Objects Based On Complex Sequential Data

This paper proposes a method that predicts attractive
evaluation objects. In the learning phase, the method inductively
acquires trend rules from complex sequential data. The data is
composed of two types of data. One is numerical sequential data.
Each evaluation object has respective numerical sequential data. The
other is text sequential data. Each evaluation object is described in
texts. The trend rules represent changes of numerical values related
to evaluation objects. In the prediction phase, the method applies
new text sequential data to the trend rules and evaluates which
evaluation objects are attractive. This paper verifies the effect of the
proposed method by using stock price sequences and news headline
sequences. In these sequences, each stock brand corresponds to an
evaluation object. This paper discusses validity of predicted attractive
evaluation objects, the process time of each phase, and the possibility
of application tasks.

• Shigeaki Sakurai
• Makino Kyoko
• Shigeru Matsumoto

• Trend rule
• frequent pattern
• numerical sequential data
• text sequential data
• evaluation object.

[1] W. Antweiler and M. Z. Frank Is All That Talk Just Noise? The
Information Content of Internet Stock Message Boards, J. of Finance,
vol.59, no.3, pp.1259-1294, 2004.
[2] J. Bollen, H. Mao, and X. -J. Zeng, Twitter Mood Predicts the
Stock Market, http://arxiv.org/PS cache/arxiv/pdf/1010/1010.3003v1.pdf,
October, 2010.
[3] Chasen, http://chasen.naist.jp/hiki/ChaSen/, 2010 (in Japanese).
[4] M. D. Choudhury, H. Sundaram, A. John, and D. D. Seligmann, Can Blog
Communication Dynamics be Correlated with Stock Market Activity?,
Proc. of the 19th ACM Conf. on Hypertext and Hypermedia, 2010.
[5] G. P. C. Fung, J. X. Yu, and W. Lam, News Sensitive Stock Trend
Prediction, Proc. of the 6th Pacific-Asia Conf. on Knowledge Discovery
and Data Mining, pp.481-493, 2002.
[6] J. Han, J. Pei, and Y. Yin, Mining Frequent Patterns without Candidate
Generation, Proc. of the 2000 ACM SIGMOD Intl. Conf. on Management
of Data, pp.1-12, 2000.
[7] M. -A. Mittermayer and G. F. Knolmayer, NewsCATS - A News
Categorization and Trading System, Proc. of the 6th IEEE Intl. Conf.
on Data Mining, pp.1002-1007, 2006.
[8] D. Peramunetilleke and R. K.Wong, Currency Exchange Rate Forecasting
from News Headlines, Proc. of the 13th Australasian Database Conf.,
vol.5, pp.131-139, 2002.
[9] S. Sakurai and K. Ueno, Analysis of Daily Business Reports based on
Sequential Text Mining Method, Proc. of the 2004 IEEE Intl. Conf. on
Systems, Man and Cybernetics, vol.4, pp.3279-3284, 2004.
[10] S. Sakurai, Y. Kitahara, and R. Orihara, Sequential Mining Method
based on a New Criterion, Proc. of the Artificial Intelligence and Soft
Computing 2006, pp.1-8, 2006.
[11] S. Sakurai, Y. Kitahara, R. Orihara, K. Iwata, N. Honda, and T. Hayashi,
Discovery of Sequential Patterns Coinciding with Analysts’ Interests, J.
of Computers, vol.3, no.7, pp.1-8, 2008.
[12] S. Sakurai, An Efficient Discovery Method of Patterns from Transactions
with their Classes, Proc. of the 2010 IEEE Intl. Conf. on Systems, Man
and Cybernetics, pp.2116-2123, 2010.
[13] Y. -W. Seo, J. A. Giampapa, and K. P. Sycaratech, Financial
News Analysis for Intelligent Portfolio Management, Report
CMU-RI-TR-04-04, Robotics Institute, Carnegie Mellon University,
January, 2004.
[14] X. Zhang, H. Fuehres, and P. A. Gloor, Predicting Stock Market
Indicators through Twitter "I hope it is not as bad as I fear”, Procedia
- Social and Behavioral Sciences, vol.26, pp.55-62, 2011.
[15] http://www.geocities.jp/sundaysoftware/csv/keiretu.html
[16] http://www11.ocn.ne.jp/˜ kui168/link37.html
[17] http://www11.ocn.ne.jp/˜ kui168/link39.html