Gracenote Discover™
A truly flexible music discovery solution, Gracenote Discover enables device and software developers and music services to provide targeted, customized recommendations and merchandizing options to complement their content offering and commercials goals and provide results tailored for each customer’s catalog items.
Personalized Recommendations and Merchandizing
Gracenote Discover delivers highly relevant recommendations for music-related content based on a “seed” derived from a specific song track or artist. Users generate recommendations from Gracenote-enabled media management and recognition applications, browsing online music stores, or by utilizing their own music collection.
Relevant Recommendations for a Global Audience
Unlike other solutions which can only produce valid recommendations for music released in a particular geographic territory, Gracenote’s Discover can be deployed virtually anywhere around the world to deliver music recommendations that hit the mark every time. Most solutions are only aware of a consumer's recently played or purchased music from a single store provider's own service. Discover can avoid such limitations by integrating with Gracenote’s MusicID® to recognize and analyze all of the songs in a user's music library, not just a subset gathered from an individual music service.
Greater Ability to Scale
The majority of music recommendation systems use a single approach to generate results. These results often do not scale due to the limitations inherent in each technique and do not keep pace with the rapidly growing digital media market. Gracenote’s Discover uses a proprietary system for generating recommendations that combines three powerful approaches.
- Editorial – Gracenote's international team of music experts is continually categorizing artists, albums, and songs into more than 3,000 micro-genres, as well as assigning other descriptive attributes such as eras, artist types, and regions. This method enables Discover’s system to consistently identify music which shares similar inherent subjective qualities, best identified by a human expert, across the global musical world.
- Track Level Descriptive Data – Automated and scalable computer-based analysis of the audio waveforms of individual songs using Digital Signal Processing (DSP) techniques can objectively determine musical characteristics such as mood, tempo, timbre, rhythm, instrumentation, harmony, melody and structure of the songs.
- Music Community – Gracenote's community of millions of music fans, using popular Gracenote-enabled media players, provides insight into global music consumption patterns. Discover utilizes this exclusive data to create geographic-specific recommendations. Customers can integrate their own sales ranking data or even third-party collaborative filtering results to augment the results delivered by the Editorial and DSP Analysis modules.
When combined in Discover these three approaches complement each other to provide more consistently accurate recommendations across all possible situations than any of the techniques can produce individually.
“White Box” Approach Puts Control in Customers’ Hands
Gracenote combines store catalog data and other inputs to create customized, targeted recommendations for users. The customer can integrate their own proprietary user data (for example, purchase history or play popularity) to help enhance the recommendations. Music services optimize and prioritize results sets to accommodate their commerce needs.
Controls available to a music service include the ability to:
- Optimize recommendations to match regional catalogs and preferences utilizing Gracenote's regional popularity statistic
- Control which similarity criteria are given the most importance
- Prioritize specific content to surface catalog items for higher promotion, such as new releases and exclusive items.
- Tailor the number and variety of recommendations presented to a consumer providing the flexibility of either a limited or wide range of popularity and similarity levels
Generate Recommendations Based on Any Album, Artist, or Song
Although Discover only recommends merchandise available from the customer's available-for-sale catalog, Discover can use essentially any song, album or artist as the starting point or "seed" for a recommendation. Any song, album or artist in the user's personal digital music collection can be used as a recommendation starting point by leveraging the Gracenote Global Media Database® - the largest and most comprehensive global database of music and video information, enhanced through relationships with more than 3,000 content owners including major and independent labels, movie studios and other media information partners. This enables new music metadata to be incorporated into the database weeks before release date, delivering up-to-the-minute song information and the most accurate and relevant recommendations.
Reliable, Rapid Deployment of Recommendation Services
Gracenote Discover is deployed within the infrastructure of the music service provider or on-line store customer, minimizing any real-time reliance on an outside service. Additionally, Discover has been architected to deliver efficient results, reducing the delays produced by excessive real-time calculations.
During initial set-up, the customer supplies Gracenote with their merchandise catalog data, along with parameters to establish global and regional sales priorities and other optional data. The depth of the Gracenote Global Media Database and pre-linking to all industry standard identifiers lets Gracenote quickly integrate and optimize the Discover service for each particular music store catalog. Because of Discover’s multi-pronged data approach, there is no requirement for customers to build up a sales history or perform detailed track-level editorial analysis before quality recommendations can be delivered.
