Emerging Technology: Recommendation Systems and Streaming Music Services
Emerging Technology
Recommendation Systems and Streaming Music Services
Management 566
Introduction Music—it is the beat of present day. How can we keep up? How do we know what music is good and what is bad? How do you find that one song that your high school sweetheart sang to you in the 80’s? What if you are just dying to hear some music that sounds like Dougie Fresh and the Get Fresh Crew, but you don’t really know where to start? Digital music is growing and the development of music recommendation is helpful for the said situations outlined above. Apple, Inc., Spotify, and Pandora are three prime examples of commercial music recommender systems that also provide music streaming services. This paper will focus on recommender systems and streaming music services, delineating current business applications and business issues.
Background
Because digital music is growing so rapidly, music recommendation is making all the difference for music lovers. Recommender systems also known as recommender platforms or engines are a subcategory of information filtering systems that seek to predict the rating or preference that a user would give to an item (Kuo et al., 2005). There are two major approaches for personalized music recommendation. The content-based filtering approach analyzes the content of music that users liked in the past and recommends music with relevant content; while the collaborative filtering approach recommends music that a peer group of similar preference has liked (Kuo et al., 2005). Both music recommendation methods are based on user preference. It is not uncommon and is actually practiced quite frequently for both approaches to be combined. This is called Hybrid Recommender Systems (McFee et al., 2012). Recommender systems have become extremely common in most recent years; Apple, Pandora, Spotify, Last.fm, and Google to name a few. Netflix and Amazon.com also use the recommender approach and have become quite saleable from
Recommendation Systems and Streaming Music Services
Management 566
Introduction Music—it is the beat of present day. How can we keep up? How do we know what music is good and what is bad? How do you find that one song that your high school sweetheart sang to you in the 80’s? What if you are just dying to hear some music that sounds like Dougie Fresh and the Get Fresh Crew, but you don’t really know where to start? Digital music is growing and the development of music recommendation is helpful for the said situations outlined above. Apple, Inc., Spotify, and Pandora are three prime examples of commercial music recommender systems that also provide music streaming services. This paper will focus on recommender systems and streaming music services, delineating current business applications and business issues.
Background
Because digital music is growing so rapidly, music recommendation is making all the difference for music lovers. Recommender systems also known as recommender platforms or engines are a subcategory of information filtering systems that seek to predict the rating or preference that a user would give to an item (Kuo et al., 2005). There are two major approaches for personalized music recommendation. The content-based filtering approach analyzes the content of music that users liked in the past and recommends music with relevant content; while the collaborative filtering approach recommends music that a peer group of similar preference has liked (Kuo et al., 2005). Both music recommendation methods are based on user preference. It is not uncommon and is actually practiced quite frequently for both approaches to be combined. This is called Hybrid Recommender Systems (McFee et al., 2012). Recommender systems have become extremely common in most recent years; Apple, Pandora, Spotify, Last.fm, and Google to name a few. Netflix and Amazon.com also use the recommender approach and have become quite saleable from
Cited: Kuo, F., Meng-Fen, C., Man-Kwan, S., & Suh-Yin, L. (2005). “Emotion-based Music Recommendation by Association Discovery from Film Music.” 507-510. Retrieved 2012-03-12 McFee, B., Ellis, D Schein, Andrew I., Popescul, Alexandrin, Ungar, Lyle H., Pennock, David M. (2002). "Methods and Metrics for Cold-Start Recommendations". pp. 253–260. Retrieved 2012-03-12. Parsons, J., Ralph, P., Gallagher, K. (2004). “Using Viewing Time to Infer User Preference in Recommender Systems.” AAAI Workshop in Semantic Web Personalization, San Jose, California. Retrieved 2012-03-12. Sarwar, B., Karypis, G., Konstan, J., Riedl, J. (2000). “Application of Dimensionality Reduction in Recommender System: A Case Study.” Retrieved 2012-04-12. McGookin, D., & Brewster, S. (2012). “Pulse: The Design and Evaluation of an Auditory Display to Provide a Social Vibe.” Retrieved 2012-04-12. PFanner, E., & O 'Brien, K. (2012, October 16). “Europe Presses Google to Change Privacy Policy.” New York Times: Global Business. Retrieved from http://www.nytimes.com/2012/10/17/business/global/17iht-google17.html?pagewanted=all Schafer, B., Konstan, J., & Riedi, J. (1999). “Recommender Systems in E-commerce.” doi: www.grouplens.org/papers/pdf/ec-99.pdf Pine, J