HYBRID RECOMMENDER SYSTEMS SURVEY AND EXPERIMENTS 349 teee resulis The las Ai rel rastan ras yot s Chois On Main o9p小p 89M的8009以Q我做碳88 39 8多 Figure 2. Similarity-based recommendation A key consideration in the design of the system was to support a natural interactive retrieval process. After the first page, no action requires more than a single click, an important consideration in efficient use of the web medium. The system presents one main result and a small number of neighbors rather than an overwhelming list and the user can explore the space of restaurants, discovering for example, the tradeoffs between price and quality for restaurants serving a given cuisine Entree's recommendation technique is one of knowledge-based similarity retrieval. There are two fundamental retrieval modes: similarity-finding and ritique-based navigation. In the similarity case, the user has selected a given item from the catalog(called the source)and requested other items similar to it. To per form this retrieval, a set of candidate entities is retrieved from the database. sorted based on similarity to the source and the top few candidates returned to the user Navigation is essentially the same except that the candidate set is filtered prior to sorting to leave only those candidates that satisfy the user's critique. For example if a user responds to item X with the tweak ' Nicer,' the system determines the niceness'value of X and rejects all candidates except those whose value is greater. Reproduced with permission of the copyright owner. Further reproduction prohibited without permissionReproduced with permission of the copyright owner. Further reproduction prohibited without permission