Definitions for "Collaborative filtering"
Keywords:  crm, recommend, amazon, tastes, visitor
The basis for this personalization method is the assumption that persons with similar tastes will also have similar interests. First, "mentors" are used to deliver explicit ratings of website content and/or of products. When a visitor accesses the website, the information about him, his interests and his behavior is compared with that of the mentors (neighborhood analysis). Recommendations are then delivered based on this. Because this procedure is very complicated and time may be of the essence, implicit ratings (shopping cart, etc.) are also included in behavior analysis, which accordingly lowers the quality of the ratings.
A feature of CRM software that allows a business to provide products or services to a customer based on what other customers with similar preferences have purchased in the past. Internet retailers use collaborative filtering to recommend popular products to you.
Personalization technology that employs recommendation engines that use advanced statistical models and other forms of intelligent software to extract trends from the behavior of Web site visitors.
a voluntary practice and method, most prevalent on the Internet, of pooling and ranking informed opinions on any particular topic. A relatively well-known example is PHOAKS (People Helping One Another Know Stuff) where anyone can post opinions of web resources in Usenet Netnews which PHOAKS reads, classifies, abstracts and tallies automatically. View records related to this term
Refers to various methods of adding together the judgements of many individuals as to the value of a particular resource. For example, the Google Search Engine ranks pages more highly in its result sets when many other Web sites have linked to these pages. The theory is, in other words, that a page with many other sites linked to it must be adjudged more valuable.
A Web interactive channel through which a company can collect information about its customers by monitoring what pages are visited on its Web site and where the most time is spent.