Research Seminar - July 09, 1999

Abstract

Users typically have to wait for information they require from the World Wide Web. Users' waiting time for information on the WWW may be reduced by pre-sending documents they are likely to request, albeit at a possible expense of additional transmission costs. In this seminar, I will describe a decision-theoretic pre-sending system developed over the past 2 years with my Monash colleagues Ingrid Zukerman and David Albrecht.

The first part of the talk will look at the problem of predicting users' requests. We considered several Markov models derived from the behaviour patterns of many users, which predict which documents a user is likely to request next. I will present comparative results of the predictive accuracy of the different models, and, based on these results, show how we can build hybrid models which combine the individual models in different ways. These hybrid models generally have a greater predictive accuracy than the individual models.

The second part of the talk will focus on a decision-theoretic approach for pre-sending documents based on the predictions made by the best hybrid model. We introduce two evaluation methods which measure the immediate and the eventual benefit of pre-sending a document. We use these evaluation methods to compare the performance of our decision-theoretic policy to that of a naive pre-sending policy, and to identify the domain parameter configurations for which each of these policies provides a clear overall benefit to the user.