Effective Use Of Mlops In Music Recommendation System

Manoharan Susila, Pradeep (2022) Effective Use Of Mlops In Music Recommendation System. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

Users’ preferences such as ratings, only give unidimensional data, but the reasons for users’ preferences might be tied to a variety of different attributes of an object. Here, item refers to things like categories or songs. We can determine the user’s interest by examining comments generated by the user. Here, we’re using the recommendations system to create a music recommendation model. Using the Spotify dataset, we extract collaborative and content-based elements to determine the user’s listing pattern. To address the shortcomings of the standard recommendation system, we added ML ops to this system. By incorporating this methodology into the prior system, we can avoid manually training the data whenever new data enters the system, which is time-consuming. However, with the new system that is being proposed, when fresh data is introduced into the system, the mops will retrain the data without the need for human interaction. We will compare ML ops accuracy to the standard technique in this research. Then, when the user’s tastes vary over time, we’ll observe how the recommendation algorithm dynamically promotes music to them.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Vikas UNSPECIFIED
Subjects:	M Music and Books on Music > M Music Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	19 Apr 2023 10:30
Last Modified:	19 Apr 2023 10:30
URI:	https://norma.ncirl.ie/id/eprint/6476

Actions (login required)

View Item