Skip to main content

Do Stock Analysts Make Good Recommendations: A Unified System for Analysts’ Performance Tracking and Ranking

  • Conference paper
  • First Online:
Information Search, Integration, and Personalization (ISIP 2013)

Abstract

Stock analyst’s report is among of several important information sources for making investment decisions, as it contains relevant information about stocks as well as recommendation where investors should buy or sell the stock together with entry and exit strategies. Good analysts should often make trustworthy recommendations so that traders following them can make regularly profits from their advices. Nevertheless, identifying good analysts is not a trivial task especially when processed manually. Particularly, one has to collect and extract strategies from unstructured texts appearing in analyst reports, backtest such strategies with historical market data, and summarize backtested results by overall profits and losses. To address these problems, we propose a unified system which makes use of a combination of information integration and computational finance techniques to automate all these tasks. Our system performs considerably well in extracting recommendations from various analysts’ reports and provides new valuable information to traders. The system has been made available online as a mobile application for community use.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Fundamental recommendations generally contain only rating information and earning estimates while technical recommendations also contain entry price, target price and stop-loss price as well as support and resistant levels.

  2. 2.

    The synonym list created by a system administrator is composed of price types and their alias names. For example, the reference price has “ref.price”, “close price” as its aliases.

  3. 3.

    This paper sets commission at 0.17 % of total transaction cost for all simulations.

References

  1. Banjongprasert, S., Isareeyapracha, K.: Investor research survey. Technical report, Capital Market Research Forum (2011)

    Google Scholar 

  2. Barber, B., Lehavy, R., McNichols, M., Trueman, B.: Can investors profit from the prophets? security analyst recommendations and stock returns. J. Finance 56(2), 531–563 (2001)

    Article  Google Scholar 

  3. Ciravegna, F.: Adaptive information extraction from text by rule induction and generalisation. In: Proceedings of the 17th International Joint Conference on Artificial intelligence, IJCAI’01, vol. 2, pp. 1251–1256. Morgan Kaufmann Publishers Inc., San Francisco (2001)

    Google Scholar 

  4. Desai, H., Jain, P.C.: An analysis of the recommendations of the superstar money managers at barron’s annual roundtable. J. Finance 50(4), 1257–1273 (1995)

    Google Scholar 

  5. Lee, Y.S., Geierhos, M.: Buy, sell, or hold? information extraction from stock analyst reports. In: Beigl, M., Christiansen, H., Roth-Berghofer, T.R., Kofod-Petersen, A., Coventry, K.R., Schmidtke, H.R. (eds.) CONTEXT 2011. LNCS, vol. 6967, pp. 173–184. Springer, Heidelberg (2011)

    Chapter  Google Scholar 

  6. Muslea, I., Minton, S., Knoblock, C.: Stalker: learning extraction rules for semistructured. In: AAAI Workshop on AI and Information Integration (1998)

    Google Scholar 

  7. Pinto, D., McCallum, A., Wei, X., Bruce Croft, W.: Table extraction using conditional random fields. In: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’03, pp. 235–242. ACM, New York (2003)

    Google Scholar 

  8. Rungruengpon, W.: The strategy to changing the saving and investment behavior of people aged between 20 to 29 years old to invest more in stock exchange. Technical report, Thammasat Business School (2013)

    Google Scholar 

  9. Stickel, S.E.: The anatomy of the performance of buy and sell recommendations. Financ. Anal. J. 51(5), 25–39 (1995)

    Article  Google Scholar 

  10. Womack, K.L.: Do brokerage analysts’ recommendations have investment value? J. Finance 51(1), 137–167 (1996)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Anon Plangprasopchok .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Yingsaeree, C., Plangprasopchok, A., Tanwanont, P., Tuchinda, R. (2014). Do Stock Analysts Make Good Recommendations: A Unified System for Analysts’ Performance Tracking and Ranking. In: Kawtrakul, A., Laurent, D., Spyratos, N., Tanaka, Y. (eds) Information Search, Integration, and Personalization. ISIP 2013. Communications in Computer and Information Science, vol 421. Springer, Cham. https://doi.org/10.1007/978-3-319-08732-0_4

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-08732-0_4

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-08731-3

  • Online ISBN: 978-3-319-08732-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics