While the World Wide Web (WWW) contains a vastquantity of information, it is often difficult forWeb users to find the information they seek. Thereare many recommender systems that are designed tohelp users find relevant information on the Web;however, as many of these systems are server-side,they can only provide information about one specificWeb site and they are typically based only oncorrelations amongst the pages that the various usersvisit. Unfortunately, there is no reason to believethat these correlated pages will necessarily containuseful information.Here, a passive Goal-Directed Complete-Web (GCW)recommender system, which recommends relevant pagesfrom anywhere on the Web without any explicitadditional input, has been developed. Afteridentifying the search strategy that is employed byactual users while they browse the Web, the modelattempts to locate the pages that satisfy the currentinformation need based on the content of the pagesthe user has visited, and the actions the user hasapplied to these pages.