Problem Definition
With the rise of digital content distribution, people now have access to music collections on an unprecedented scale. Commercial music libraries easily exceed 15 million songs, which vastly exceeds the listening capability of any single person. With millions of songs to choose from, people sometimes feel overwhelmed. Thus, an efficient music recommender system is necessary in the interest of both music service providers and customers. Users will have no more pain to make decisions on what to listen while music companies can maintain their user group and attract new users by improving users’ satisfaction. This music recommendation system also helps the users to listen to the music based on their mood using which, an angry person can calm himself down by listening to the recommended songs.
Motivation
Many music streaming services, such as Pandora and Spotify, are developing high-precision commercial music recommendation systems at the moment. These businesses make money by assisting customers in finding appropriate music and charging them for the quality of their recommendations. As a result, there is a thriving market for good music recommendation systems.
Scope of Project
- Music recommendation will be based on mood of the user which will be get from user’s facial expression.
- We will use an already existing streaming service in order to retrieve and play music as it is not in the scope of the project to develop our own music streaming service. We decided to use Spotify because of their extensive APIs and SDKs which are easy to use.
- Spotify also offers access to a large amount of audio feature data connected to the music which we retrieve and use in the recommender system.
- This music recommendation will be available through a web application where music will be displayed to user based on their facial expression and their previous watch history to enhance the search result.
- After selecting the music, user can play it on our web application.