TasteKeeper is the public face of the AURA Project of Sun Microsystems Laboratories. The AURA Project was started to investigate new recommender technologies. A recommender system provides recommendations for items (books, music, movies, etc.) based on a user's previous preferences (books they've read, music they've listened to, etc.).

Current recommender systems rely on the wisdom of the crowds using a technique called collaborative filtering. In a collaborative filtering system, the similarity between two items (e.g., books, songs, movies) is determined by looking at what users have consumed the items. Items that have been consumed by many similar users are considered to be similar. Unfortunately, this approach has several drawbacks that can ultimately lead to poor recommendations.

TasteKeeper takes a novel approach to recommendation, avoiding many of the problems inherent in standard recommender systems. In addition to representing an item by the users that have consumed it, we also represent an item using a textual aura that can be gathered from social tags applied to the items, reviews of the items, blog posts about the items, and even the content of the items themselves.

• Learn more about TasteKeeper's recommendations

The heart of the TasteKeeper system is the AURA Project Data Store. The Data Store was designed to be a distributed, scalable, reliable data store that could be used as a repository for item data and metadata. It also stores user information and attention data that could be used by recommenders for various item types. Our aim is to be able to store information about millions of items and potentially billions of attention data points.

• Learn more about the AURA Project Data Store
• Get the AURA Project source code

The Music Explaura is a musical artist recommendation application built using TasteKeeper as its back end. Users can find artists they like, accentuate the aspects of those artists they enjoy the most and get recommendations for other artists. Users can steer the recommendations by adding terms that describe what they want and see explanations of why particular artists were recommended.

• Steve's blog post explaining the Music Explaura
• A screencast demo of the Music Explaura

In the near future we will be releasing the AURA Project in open source so that others can use and contribute to the project.

Some resources for learning more about The AURA Project:

• TasteKeeper's recommendation technology
• The Music Explaura
• A description of the Music Explaura's transparent, steerable recommendations
• A screencast demo of the Music Explaura
• The TasteKeeper discussion forums
• The AURA Project source code