Presentation on theme: "Link Prediction and Path Analysis using Markov Chains"— Presentation transcript:
1Link Prediction and Path Analysis using Markov Chains (R. R. Sarukkai)Presentation by H.Perrin, S.Jaffer, S.Lambert & W.Lewis1
2Link Prediction & Path Analysis Volume of pages makes efficient WWW navigation difficultAim: To analyse users' navigation history to generate tools that increase navigational efficiencyie. Predictive server prefetchingProvides tools for other work previously done.
3The Author: Ramesh R. Sarukkai Researches Internet technologiesMember of W3C committeeNow works for Yahoo!
9HTTP Request Prediction In server or proxyAllows pre-fetching of most likely pages firstConnection latency is minimsedServer efficiency increases
10Link Suggestion (Adaptive Web Navigation) Link prediction used to offer links to users based on previous navigation historySimilar technique has been applied (ie. Amazon)But not necessarily using Markov ChainsCan be client or server side
11Tour Generation Given a start URL, user guided along path of links Appropriate to user's interestsSequentially pick the next most popular linkNon-cyclic
12Hub/Authority Identification Kleinberg proposed Web 'Hub/Authorities'Hub: Web site that is a good starting point for finding identificationAuthority: Web site that contains useful information on a particular topic.Hub/Authority weighting given in Markov transitional weighting