Advertisement

Business Analytics for Price Trend Forecasting through Textual Data

  • Marco PospiechEmail author
  • Carsten FeldenEmail author
Chapter
  • 1.1k Downloads
Part of the Palgrave Studies in Democracy, Innovation, and Entrepreneurship for Growth book series (DIG)

Abstract

Various data sources are available in the era of Big Data to increase business understanding. For example, price predictions based on news ticker offers a broad range of valuable information. An automatic analysis is able to support traders in their daily business to maximize profits. But, only little is known about this topic, yet. In cooperation with a globally acting company, we developed a generalizable approach to use news tickers for price trend forecasts. First, we realized that the effect on prices by news tickers is complex to identify. Second, irrelevant tickers decrease the performance. Several approaches are evaluated to identify relevant articles in an automatic fashion, whereby the functionality is demonstrated in two different case studies. The results are practicable. Our research contributes to the discussion about business analytics, business cases, and their realization. It can be applied in any domain where important events have to be considered instantly.

Keywords

Price prediction Text mining Gas market Oil market Big Data Business intelligence 

References

  1. Breiman, Leo, Jerome Friedman, Charles J. Stone, and Richard A. Olshen. 1984. Classification and Regression Trees. Belmont: Wadsworth.Google Scholar
  2. Busse, Sebastian, Patrick Helmholz, and Markus Weinmann. 2012. Forecasting day ahead spot price movements of natural gas—An analysis of potential influence factors on basis of a NARX neural network. Paper Presented by the Multikonferenz Wirtschaftsinformatik, Braunschweig, Germany.Google Scholar
  3. Chan, Yue-cheong, Andy C.W. Chui, and Chuck C.Y. Kwok. 2001. The impact of salient political and economic news on the trading activity. Pacific-Basin Finance Journal 9(3): 195–217.CrossRefGoogle Scholar
  4. Chang, Yin-Wen, Cho-Jui Hsieh, and Kai-Wei Chang. 2010. Training and testing low-degree polynomial data mappings via linear SVM. Journal of Machine Learning Research 11(4): 1471–1490.Google Scholar
  5. Chawla, Nitesh V., Nathalie Japkowicz, and Aleksander Kolcz. 2004. Editorial: Learning form imbalanced datasets. SIGKDD Explorations Newsletter 6(1): 1–6.CrossRefGoogle Scholar
  6. Davenport, Thomas, and Jeanne Harris. 2007. Competing on Analytics: The New Science of Winning. Boston: Harvard Business School Press.Google Scholar
  7. Duarte, Andre, Jose Nuno Fidalgo, and Joao Tomé Saraiva. 2009. Forecasting electricity prices in spot markets—One week horizon approach. Paper Presented by the IEEE PowerTech, Bucharest, Romania.Google Scholar
  8. Fayyad, Usama, Gregory Piatetsky-Shapiro, and Padhraic Smyth. 1996. From data mining to knowledge discovery. In Advances in Knowledge Discovery and Data Mining, ed. Usama Fayyad, Gregory Piatetsky-Shapiro, and Padhraic Smyth. Menlo Park: AAAI Press.Google Scholar
  9. Felden, Carsten, and Peter Chamoni. 2003. Web farming and data warehousing for energy tradefloors. Paper Presented by the IEEE Web Intelligence WI.Google Scholar
  10. Gartner. 2013. Hype cycle for big data. https://www.gartner.com/doc/2574616. Accessed 28 April 2014.
  11. Geva, Tomer, and Jacob Zahavi. 2010. Predicting intraday stock returns by integrating market data and financial news reports. Paper Presented by the Mediterranean Conference on Information Systems MCISS.Google Scholar
  12. Khandar, Punam V., and Sugandha V. Dani. 2010. Knowledge discovery and sampling techniques with data mining for identifying trends in data sets. International Journal on Computer Science and Engineering (IJCSE) (Special Issue): 7–11.Google Scholar
  13. Labrinidis, Alexandros, and Hosagrahar Jagadish. 2012. Challenges and opportunities with big data. Proc. VLDB Endowment 5(12): 2032–2033.CrossRefGoogle Scholar
  14. Lavrenko, Victor, Matt Schmill, Dawn Lawrie, Paul Ogilvie, David Jensen, and James Allan. 2000. Language models for financial news recommendation. Paper Presented by the Proceedings of the Ninth International Conference on Information and Knowledge Management, McLean, Virginia, USA.Google Scholar
  15. Li, Guang, Chen-Ching Liu, and Chris Mattson. 2007. Day-ahead electricity price forecasting in a grid environment. Transactions on Power Systems 22(1): 266–274.CrossRefGoogle Scholar
  16. Lin, Boqiang, and Presley K. Wesseh. 2013. What causes price volatility and regime shifts in the natural gas market. Energy 55(2013): 553–563.CrossRefGoogle Scholar
  17. Linn, Scott C., and Zhen Zhu. 2004. Natural gas prices and the gas storage report: Public news and volatility in energy futures markets. Journal of Futures Markets 24: 283–313.CrossRefGoogle Scholar
  18. Lo, Andrew W., and Craig A. MacKinlay. 1999. A Non-Random Walk Down Wall Street. Princeton, New Jersey: Princeton University Press.Google Scholar
  19. Malliaris, Mary E., and Steven G. Malliaris. 2005. Forecasting energy product prices. Paper Presented by the IEEE Proceedings of International Joint Conference on Neural Networks, Montreal, Canada.Google Scholar
  20. Miner, Gary, Dursun Delen, Andrew Fast, and John Elder. 2012. Practical Text Mining and Statistical Analysis for Non-structured Text Data. Waltham: Academic Press.Google Scholar
  21. Mitchell, Tom. 1997. Machine Learning. Boston: McGraw Hill.Google Scholar
  22. Mittermayer, Marc-André. 2004. Forecasting intraday stock price trends with text mining techniques. Paper Presented by the IEEE Computer Society, Proceedings of the 10th Annual Hawaii International Conference on System Sciences, Big Island, Hawaii, USA.Google Scholar
  23. Nann, Stefan, Jonas Krauss, and Detlef Schoder. 2013. Predictive analytics on public data—The case of stock markets. Paper Presented by the ECIS, Sofia, Bulgaria.Google Scholar
  24. Ni, E., and Peter Luh. 2001. Forecasting power market clearing price and its discrete PDF using a Bayesian-based classification method. Paper Presented by the Power Engineering Society Winter Meeting.Google Scholar
  25. Oh, C., and O. Sheng. 2011. Investigating predictive power stock micro blog sentiment in forecasting future stock price directional movement. Paper Presented by the International Conference on Information Systems, Shanghai, China.Google Scholar
  26. Pospiech, Marco, and Carsten Felden. 2012. Big data—A state-of-the-art. Paper Presented by the AMCIS, Seattle, USA.Google Scholar
  27. ———. 2013. A descriptive big data model using grounded theory. Paper Presented by the IEEE Big Data Science and Engineering, Sydney, Australia.Google Scholar
  28. ———. 2014. Towards a price forecast model for the German electricity market based on structured and unstructured data. Paper Presented by the Multikonferenz Wirtschaftsinformatik MKWI, Paderborn, Germany.Google Scholar
  29. Pring, Martin J. 1991. Technical Analysis Explained. New York, NY: McGraw-Hill.Google Scholar
  30. Rapid-I Incorporation. 2013. Rapid-I report the future. http://rapid-i.com/. Accessed 28 April 2014.
  31. Roomp, Kirsten, Iris Antes, and Thomas Lengauer. 2010. Predicting MHC Class I epitopes in large datasets. BMC Bioinformatics 11(1): 1–90.CrossRefGoogle Scholar
  32. Schumaker, Robert P., and Hsinchun Chen. 2006. Textual analysis of stock market prediction using financial news articles. Paper Presented by the 12th Americas Conference on Information Systems AMCIS, Acapulco, Mexico.Google Scholar
  33. Turban, Efraim, Jay E. Aronson, and Ting-Peng Liang. 2004. Decision Support Systems and Intelligent Systems. 7th ed. Upper Saddle River, N.J: Prentice Hall.Google Scholar
  34. Wuthrich, Beat, Vincent Cho, and Jian Zhang. 1998. Daily stock market forecast from textual web data. Paper Presented by the IEEE International Conference on Systems, Man, and Cybernetics. Google Scholar
  35. Zhang, Li, and Peter Luh. 2002. Power market clearing price prediction and confidence interval estimation with fast neural network learning. Paper Presented by the Power Engineering Society Winter Meeting.Google Scholar

Copyright information

© The Author(s) 2017

Authors and Affiliations

  1. 1.TU Freiberg, Institute of Information ScienceFreibergGermany

Personalised recommendations