Advertisement

The Business Analyzer: A Second Generation Approach to Financial Decision Support

  • Walter Hamscher

Abstract

The Business Understander is the architecture of a next generation knowledge-based facility for supporting the understanding of client businesses by Price Waterhouse practitioners. A key component is the Business Analyzer, which finds anomalies in financial results and computes explanations for them. Causal knowledge is represented in the form of constraints among financial variables, while empirical knowledge is represented as probability distributions over alternative assumptions, including modeling assumptions and assumptions about external perturbations. The task of auditing financial statements is used to illustrate the role of these types of reasoning in the Business Analyzer.

Keywords

Exogenous Variable Empirical Knowledge Qualitative Reasoning Client Firm Business Analyzer 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D. Bobrow, editor. Qualitative Reasoning about Physical Systems. MIT Press, Cambridge, MA, 1985. Also Artificial Intelligence 24.Google Scholar
  2. 2.
    M. J. Bouwman. Human diagnostic reasoning by computer: An illustration from financial analysis. Management Science, 29(6):653–672, June 1983.CrossRefGoogle Scholar
  3. 3.
    B. D’Ambrosio. Extending the mathematics in qualitative process theory. In Proc. 6th National Conf. on Artificial Intelligence, pages 595–599, Seattle, WA, August 1987.Google Scholar
  4. 4.
    R. Davis and W. C. Hamscher. Model-based reasoning: Troubleshooting. In H. E. Shrobe, editor, Exploring Artificial Intelligence: Survey Talks from the National Conferences on Artificial Intelligence, pages 297–346. Morgan Kaufmann, San Mateo, Calif., 1988. Also in: P. H. Winston and S. A. Shel-lard (eds.), Artificial Intelligence at MIT: Expanding Frontiers (Cambridge, Mass., MIT Press, 1990), v.1, pp. 380–429, and in W. C. Hamscher, J. de Kleer and L. Console (eds), Readings in Model-based Diagnosis (Morgan Kaufmann, San Mateo, Calif., 1992).Google Scholar
  5. 5.
    J. de Kleer. An assumption-based TMS. Artificial Intelligence, 28(2):127–162, 1986. Also in: Ginsberg, M. L. (ed) Readings in Nonmonotonic Reasoning (Morgan Kaufmann, Los Altos, CA, 1987) 280–297.CrossRefGoogle Scholar
  6. 6.
    J. de Kleer and B. C. Williams. Diagnosis with behavioral modes. In Proc. 11th Int. Joint Conf. on Artificial Intelligence, pages 1324–1330, Detroit, MI, 1989. Aiso in: W. C. Hamscher, L. Console, and J. de Kleer (eds), Readings in Model-based Diagnosis (Morgan Kaufmann, San Mateo, Calif., 1992).Google Scholar
  7. 7.
    J. de Kleer and B. C. Williams, editors. Qualitative Reasoning about Physical Systems II. Elsevier, Amsterdam, October 1991. Artificial Intelligence 51.Google Scholar
  8. 8.
    V. Dhar, B. Lewis, and J. Peters. A knowledge-based model of audit risk. AI Magazine, 9(3):57–63, Fall 1988.Google Scholar
  9. 9.
    J. W. Elliott and H. L. Uphoff. Predicting the near term profit and loss statement with an econometric model: A feasibility study. Journal of Accounting Research, pages 259–274, Autumn 1972.Google Scholar
  10. 10.
    B. Falkenhainer and K. D. Forbus. Compositional modeling: Finding the right model for the job. Artificial Intelligence, 51(1–3):95–143, 1991. Also in: J. de Kleer and B. Williams (eds.) Qualitative Reasoning about Physical Systems II (North-Holland, Amsterdam, 1991 / MIT Press, Cambridge, Mass., 1992).CrossRefGoogle Scholar
  11. 11.
    K. D. Forbus. Qualitative physics: Past, present, and future. In H. E. Shrobe, editor, Exploring Artificial Intelligence: Survey Talks from the National Conferences on Artificial Intelligence, pages 239–296. Morgan Kaufmann, San Mateo, Calif., 1988.Google Scholar
  12. 12.
    K. D. Forbus and J. de Kleer. Building Problem Solvers. MIT Press, Cambridge, MA, 1992.Google Scholar
  13. 13.
    W. C. Hamscher. Business as a domain for model-based reasoning: A proposal to use explicit representation of the structure and behavior of business entities to assess audit risk. Technical Report 4, Price Waterhouse Technology Centre, Menlo Park, CA 94025, May 1989. Also in Working Notes of the Workshop on Model-based Reasoning (International Joint Conferences on Artificial Intelligence, Menlo Park, Calif., 1989).Google Scholar
  14. 14.
    W. C. Hamscher. Explaining unexpected financial results. Technical Report 11, Price Waterhouse Technology Centre, Menlo Park, CA 94025, January 1990. Also in Working Notes of the Spring Symposium on Automated Abduction, 96–100 (AAAI Press, Menlo Park, Calif., March 1990).Google Scholar
  15. 15.
    W. C. Hamscher. ACP: Reason maintenance and inference control for constraint propagation over intervals. In Proc. 9th National Conf. on Artificial Intelligence, pages 506–511, Anaheim, CA, July 1991. Also in: W. C. Hamscher, L. Console, and J. de Kleer (eds), Readings in Model-based Diagnosis (Morgan Kaufmann, San Mateo, Calif., 1992).Google Scholar
  16. 16.
    W. C. Hamscher. Model-based financial data interpretation. In 1st Int. Conf on AI Applications on Wall Street, New York, October 1991. IEEE Computer Society Press. Also in Working Notes of the Model-based Reasoning Workshop (AAAI Press, Menlo Park, CA, 1991) and Working Notes of the 2nd International Workshop on Principles of Diagnosis (Technical Report RT/DI/91-10-7, Dipartimento di Informatica, Universitá di Torino, 1991).Google Scholar
  17. 17.
    W. C. Hamscher, L. Console, and J. de Kleer, editors. Readings in Model-based Diagnosis. Morgan Kaufmann, San Mateo, Calif., August 1992.Google Scholar
  18. 18.
    E. A. Helfert. Techniques of Financial Analysis. Homewood, 1986.Google Scholar
  19. 19.
    S. Kaufman. Report Finds Massive Fraud at MiniScribe. San Jose Mercury News, page 4D, September 12, 1989.Google Scholar
  20. 20.
    D. W. Kosy and B. P. Wise. Self-explanatory financial models. In Proc. 4th National Conf on Artificial Intelligence, pages 176–181, Austin, TX, August 1984.Google Scholar
  21. 21.
    MiniScribe. Summary of Report of the Independent Evaluation Commmit-tee of the Board of Directors of MiniScribe Corporation. Exhibit provided in 8-K Disclosure, September 12, 1989.Google Scholar
  22. 22.
    J. M. Peters. A cognitive computational model of risk hypothesis generation. Journal of Accounting Research, 28(Supplement):83–103, 1990.CrossRefGoogle Scholar
  23. 23.
    M. Selfridge, S. F. Biggs, and G. R. Krupka. GCX: A cognitive expert system for making going-concern judgements. Technical Report 86-20, University of Connecticut Department of Computer Science and Engineering and Computer Applications and Research Center, Storrs, CT 06268, December 1986.Google Scholar
  24. 24.
    D. S. Weld and J. de Kleer. Readings in Qualitative Reasoning about Physical Systems. Morgan Kaufmann, San Mateo, Calif., 1990.Google Scholar
  25. 25.
    A. Zipser. How Pressure to Raise Sales Led MiniScribe to Falsify Numbers. Wall Street Journal, page 1, September 11, 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1993

Authors and Affiliations

  • Walter Hamscher
    • 1
  1. 1.Price Waterhouse Technology CentreMenlo ParkUSA

Personalised recommendations