Implementing a Rating-Based Item-to-Item Recommender System in PHP/SQL

Abstract

User personalization and profiling is key to many succesful Web sites. Consider that there is considerable free content on the Web, but comparatively few tools to help us organize or mine such content for specific purposes. One solution is to ask users to rate resources so that they can help each other find better content: we call this rating-based collaborative filtering. This paper presents a database-driven approach to item-to-item collaborative filtering which is both easy to implement and can support a full range of applications.

Keywords

Item-based Collaborative Filtering, Recommender Systems, e-Commerce

Reference

Daniel Lemire, Sean McGrath, Implementing a Rating-Based Item-to-Item Recommender System in PHP/SQL, Technical Report D-01, January 2005.

Download

• Implementing a Rating-Based Item-to-Item Recommender System in PHP/SQL (pdf)

Hint : It is sometimes necessary to hold down shift while clicking in order to save a document.

Software

• PHP code for collaborative filtering as plain text

This code was found to be useful by several users, but you are expected to be knowledgeable in SQL and PHP to use it.

BibTeX

@TechReport{LemireTRD01,
   author    = {Daniel Lemire and Sean McGrath},
   title     = {Implementing a Rating-Based Item-to-Item Recommender System in PHP/SQL},
   institution = {Ondelette.com},
   year      = {2005},
   month={January},
   number ={D-01},
   url = {http://www.daniel-lemire.com/fr/documents/publications/webpaper.pdf}
}

Author

• Daniel Lemire: lemire at acm.org
• Sean McGrath

Related work

• Bryan O'Sullivan wrote an excellent tutorial in the same spirit, but for Python.
• Daniel Lemire's publications
• inDiscover: music recommender web site using the Weighted Slope One algorithm described in the paper
• James Thornton's list of collaborative filtering research papers

Citations

This report talks about the implementation of the following paper:

• Daniel Lemire, Anna Maclachlan, Slope One Predictors for Online Rating-Based Collaborative Filtering, In SIAM Data Mining (SDM'05), Newport Beach, California, April 21-23, 2005.

The report was cited in the following paper:

• Umardand Shripad Manikrao, T.V.Prabhakar, Dynamic Selection of Web Services with Recommendation System, International Conference on Next Generation Web Services Practices, August 2005, Seoul, Korea.

Note that I don't encourage citing this technical report only, please cite the SIAM Data Mining paper also.