Advertisement

Algorithm for Intelligent Prediction of Requests in Business Systems

  • Piotr Kalita
  • Igor Podolak
  • Adam Roman
  • Bartosz Bierkowski
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4910)

Abstract

We present an algorithm for intelligent prediction of user requests in a system based on the services hosted by independent providers. Data extracted from requests is organized in a dynamically changing graph representing dependencies between operations and input arguments as well as between groups of arguments mutually coexisting in requests. The purpose of the system is to suggest the possible set of future requests basing on the last submitted request and the state of the graph. Additionally the response time may be shortened owing to the background executing and caching of the requests most likely to be asked. The knowledge extracted from the graph analysis reveals the mechanisms that govern the sequences of invoked requests. Such knowledge can help in semi-automatic generation of business processes. The algorithm is a part of ASK-IT (Ambient Intelligence System of Agents for Knowledge-based and Integrated Services for Mobility Impaired users) EU project.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ashamala, J.: User modelling on the world wide web. Master’s thesis, Monash University, Melbourne (2004)Google Scholar
  2. 2.
    ASK-IT: Ambient Intelligence System of Agents from Knowledge Based and Integrated Services for Mobility Impaired Users, Eurepean Union 6th Framework project, http://www.ask-it.org
  3. 3.
    Gery, M., Haddad, H.: Evaluation of web usage mining approaches for user’s next query prediction. In: Proceedings of WIDM 2003, pp. 74–81 (2003)Google Scholar
  4. 4.
    Haffner, E.-G., Roth, U., Engel, T., Meinel, C.: Modeling of time and document aging for request prediction - one step further. In: Proceedings of Symposium on Applied Computing ACM SAC, pp. 984–990 (2000)Google Scholar
  5. 5.
    Hastie, H., Tibshiranie, R., Friedman, J.: The elements of statistical learning. Springer, Heidelberg (2001)zbMATHGoogle Scholar
  6. 6.
    Kantardzic, M.: Data Mining, Concepts, Models, Methods and Algorithms. IEEE Computer Society, Wiley-Interscience (2003)Google Scholar
  7. 7.
    Li, I.T., Yang, Q., Wang, K.: Clasification pruning for web request prediction. In: WWW 2001. Proceedings of the 10th World Wide Web Conference (2001)Google Scholar
  8. 8.
    Mancini, E., Villano, U., Mazzocca, N., Rak, M., Torella, R.: Performance-driven developement of a web services application using metapl/hesse. In: PDP 2005. Proceedings of 13th Euromicro Conference on Parallel, Distributed and Network-Based Processing, pp. 12–19 (2005)Google Scholar
  9. 9.
    Su, Z., Yang, Q., Lu, Y., Zhang, H.-J.: Whatnext: A prediction system for web requests using n-gram sequence models. In: WISE 2000. Proceedings of the 1st International Conference on Web Information System and Engineering, pp. 200–207 (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Piotr Kalita
    • 1
  • Igor Podolak
    • 1
  • Adam Roman
    • 1
  • Bartosz Bierkowski
    • 1
  1. 1.Institute of Computer ScienceJagiellonian UniversityKrakowPoland

Personalised recommendations