BACKGROUND. Examples of Successful Recommender Systems
Amazon recommends what books you might like to buy next based on your previous purchases and the purchases of others who bought the books you bought.
ChoiceStream culls user preferences to develop marketing strategies for online shopping, television (based on what TV shows are watched), and mobile phones (based on information such as ringtones and downloads.
MovieLens is a recommender system that uses collaborative filtering to provide you with movie recommendations based on your personal references. You preferences are matched with the preferences of other users with similar movie preferences. Visit the site for a tour of the service. MovieLens is a project of GroupLens Research.
Netflix recommends movies based on member reviews, critic reviews, popular rental lists and how you rate movies. Moviefinder and Movielens are other movie recommender systems.
Pandora™ emerged from the Music Genome Project™ and involves analysis of music by a team of musician-analysts, who study each song against nearly 400 attributes and makes this information available to the public. Users enter their favorite songs and artists into Pandora, then Pandora recommends similar music which is available through their site.
StumbleUpon gathers user ratings, using a collaborative opinion rating system to match users with websites based on their preferences and enabling users to rate sites for others to check.
|MaxMind - determines the geographical location of website visitors based on IP addresses for applications such as fraud detection, content localization, geo-targeted ads, traffic analytics, digital rights management, and regulatory compliance.
|Rocketinfo - provides personalized information solutions to organizations. Solutions based on e-Intelligence Platform consisting of proprietary neural network and intelligent agent technologies.
|CRM Guru - news/community site for the CRM industry
|Changing Worlds - ClixSmart range of personalization toolkits to build smart applications for digital TV, portals, e-commerce and mobile domains.
|InfoSplit - offers geotargeting using Netlocator, which can pinpoint the location of any IP address. Can be used to build real-time targeted pages and to generate market reports.
|Quova - solutions for companies that want to use the geographic location of web site visitors to enhance their security, marketing or regulatory compliance.
|Digital Envoy - IP Intelligence solutions that uses IP addresses to non-invasively uncover information about online users such as location, domain name and connection speed for applications including online advertising, customization, local search, analytics and online fraud prevention.
|Radica - personalization and eCRM vendor in Asia, focusing on the development of enterprise-scale eCRM, knowledge management and e-intelligence software with Artificial Intelligence technology.
|Java IP Address Locator - for Java developers who want to use geographic location in their applications. Code is based on a customized local whois database that can perform over half a million lookups per second.
|SiteBrand - enables companies to capture real-time website performance analytics, deliver targeted content via the web and e-mail, and personalize communication.
|IP Address Geolocation - provides technology to identify visitor's geographical location ie. country, region, city and ISP, using a proprietary IP address lookup database.
|TheResearch.com - CRM analytics and marketing strategy solutions to turn data into strategic information.
|Ecensity - provides an affordable, non-invasive, personalization solution for Java-based web applications and sites using profiles and rules.
|Corechange - with Coreport enterprise portals, users can create their own portals, add specialized content, assemble dynamic business processes, and manage online communities.
market leader in collaborative filtering-based recommender systems.
Blue Martini – CRM
Engage – Helps marketers target online audiences. Data analysis and OLAP tools.
Epiphany – Data mining and recommender systems.
Programs and Projects
Agents Research Lab
Center for Web Intelligence – Joomla
Duine Hybrid Recommender
IAM Group, University of Southhampton
Thomas Hofmann - publications
John Reidl - GroupLens Research Project
Paul Resnick - publications
Lyle Ungar - publications
Hal Varian - publications
- Malone, T.W., Grant, K.R., Turbak, F.A., Brobst, S.A. and Cohen, M.D. (1987) Intelligent Information Sharing Systems. Communications of the ACM, 30, 5, pp. 390-402. Available for fee from: http://www.acm.org/pubs/citations/journals/cacm/1987-30-5/p390-malone/
- Goldberg, D., D. Nichols, B. M. Oki, and D. Terry. Using collaborative filtering to weave an information tapestry. CACM, 35(12):61--70, Dec 1992.
- Paul Resnick et al. GroupLens: An Open Architecture for Collaborative Filtering of Netnews, Internal Research Report, MIT Center for Coordination Science, March 1994. http://www-sloan.mit.edu/ccs/1994wp.html
- Will Hill, Larry Stead, Mark Rosenstein and George Furnas. "Recommending And Evaluating Choices In A Virtual Community Of Use" in Proceedings of ACM Conference on Human Factors in Computing Systems, CHI'95.http://www.acm.org/sigchi/chi95/proceedings/papers/wch_bdy.htm
- Upendra Shardanand and Pattie Maes. Social Information Filtering: Algorithms for Automating "Word of Mouth", in Proceedings of ACM Conference on Human Factors in Computing Systems, CHI'95. http://www.acm.org/sigchi/chi95/proceedings/papers/us_bdy.htm
- Recommender Systems. Special section in Communications of the ACM, Vol. 40, No. 3; March 1997
- Kautz H, Selman B, Shah M Referral web: Combining social networks and collaborative filtering CACM 40: (3) 63-65, 1997
- Konstan JA, Miller BN, Maltz D, et al. GroupLens: Applying collaborative filtering to Usenet news CACM 40: (3) 77-87, 1997