Recommender System
Discussion Prompt
Your task is to analyze an existing recommender system that you find interesting.
You should:
1. Perform a Scenario Design analysis as described below. Consider whether it makes sense for your selected recommender system to perform scenario design twice, once for the organization (e.g. Amazon.com) and once for the organization’s customers.
2.Attempt to reverse engineer what you can about the site, from the site interface and any available information that you can find on the Internet or elsewhere.
3.Include specific recommendations about how to improve the site’s recommendation capabilities going forward.
4.Create your report using an R Markdown file, and create a discussion thread with a link to the GitHub repo where your Markdown file notebook resides. You are not expected to need to write code for this discussion assignment.
Scenario Design
For this Discussion I have chosen to discuss about Spotify.Spotify is a Digital, cloud-based music platform that provides cross-device access to over 50 million songs, and a rapidly-rising number of podcasts and videos. Founded in Stockholm in 2008.
Who are Spotify’s targeted users?
Millenials are the prominent users of spotify. Millenials belong to the age group of 25 to 34. Spotify’s app is really user friendly. it is available in ios, android and windows system as well. Spotify mostly tatgets millenials and Genaration Z.
What are their key goals?
Spotify aims to provide music entertainment to it’s listeners. Their motto is to let listeners listen to music what they want and when they want.Spotify acts as a personal radio.
How can you help them accomplish these goals?
Easy access to account set up.
Displaying top ranked songs,and podcasts.
Providing the option to like any songs or podcasts so that a playlist can be created.
Understanding users preferrence and suggesting music or podcast according to that preference.
Reverse Engineer:
Sopity has devloped a mathematical model to understand the relationship between artist and listeners. Spotify maps out every musical genre based on their interrelatedness. Spotify’s recommender system works based on user’s historic interactions.
There are three recommendation models at work on Spotify:
Collaborative filtering: Uses user’s behavior and that of similar users. This model implements “nearest neighbors” to make predictions about what other users might enjoy.
Natural Language Processing (NLP): It is used for song lyrics, playlists, blog posts, social media comments. NLP model can turn playlists into text doccuments and how lyrical patterns relate to each other.
Audio models: This model is Used on raw audio. This model processes raw audio to produce a range of characteristics, including key, tempo, and even loudness. By using this model spotify can slot songs into right playlists.
Recommendations:
Music Profiles:
Music profiles will integrate user’s preferences over a timeline. One can understand the evaluation of their own preferences through analyzing timelines. Through music profiles user’s family and friends can also share their preferences. Music Profiles can create a scope of conversation among people regarding music and podcasts.
References: