On the quantification of e-business capacity

ABSTRACT

In order for current e-Businesses to mature from hastily assembled systems and applications, formal processes must be put in place for planning and budgeting, pricing and costing, and for establishing quality of service and service--level assurances. There are many challenges that e-Businesses face in formalizing these processes. The most important problem is to bridge the semantic disconnect between business objectives and the information system performance objectives. Next, the characterization of the e-Business infrastructure is extremely complex, given the variety of applications and system configurations at a web site and the traffic it receives. Finally, e-Businesses need to associate and apply traditional economic factors, such as depreciation and usage to applications, operating systems, and databases. In this paper, we propose an approach for defining and quantifying effective e-Business capacity that allows us to translate quality of service objectives into the number of users that a web site can support. This approach is based on inducing online models using machine learning and statistical pattern recognition techniques. As a consequence, the approach is flexible: it adapts to any site configuration and environment. The concept of e-Business capacity allows us to naturally answer planning and operational questions about the information system infrastructure needed to support the e-Business. The questions range from indicating which performance measures in the system are "important" to simulating "if-then" scenarios

REFERENCES

• 1: Christopher M. Bishop, Neural networks for pattern recognition, Oxford University Press, Oxford, 1996
• 2: M.DeGroot.Probability and Statistics . Addison-Wesley,1989.
• 3: R.O.DudaandP.E.Hart.Pattern Classi .cation and Scene Analysis .Wiley,New York,1973.
• 4: B.Efron and R.Tibshirani.An Introduction to the Bootstrap .Chapman &Hall,1993.
• 5: J.Ertel and E.Fowlkes.Some algorithms for linear spline and piecewise multiple linear regression. Journal of the American Statistical Association , 71(355):640 -648,1976.
• 6: Nir Friedman , Dan Geiger , Moises Goldszmidt, Bayesian Network Classifiers, Machine Learning, v.29 n.2-3, p.131-163, Nov./Dec. 1997 [doi>10.1023/A:1007465528199]
• 7: N.Friedman,M.Goldszmidt,and A.Wyner.Data analysis with bayesian networks:A bootstrap approach.In Proceedings of Uncertainty in AI ,1999.
• 8: M.Goldszmidt and B.Sabata.Clustering probability distributions for characterizing urls.Technical Report TR-03,Peakstone Corporation,2001.
• 9: D.Hosmer and S.Lemeshow.Applied Logistic Regression .Wiley Interscience,1989.
• 10: Daniel A. Menascé , Virgílio A. F. Almeida, Capacity planning for Web performance: metrics, models, and methods, Prentice-Hall, Inc., Upper Saddle River, NJ, 1998
• 11: L.Oliver.The Cost Management Toolbox .AMACOM, American Management Association,NY,1990.
• 12: Judea Pearl, Probabilistic reasoning in intelligent systems: networks of plausible inference, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1988
• 13: Fernando Pereira , Naftali Tishby , Lillian Lee, Distributional clustering of English words, Proceedings of the 31st annual meeting on Association for Computational Linguistics, p.183-190, June 22-26, 1993, Columbus, Ohio [doi>10.3115/981574.981598]

INDEX TERMS

Primary Classification:
  K. Computing Milieux
  K.4 COMPUTERS AND SOCIETY
      K.4.4 Electronic Commerce

Additional Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Statistical computing

  J. Computer Applications
  J.1 ADMINISTRATIVE DATA PROCESSING
      Subjects: Business

General Terms:
Management, Performance, Theory