Enhancing Music Recommendations with Machine Learning Techniques

Konreddy, Naveen Reddy (2023) Enhancing Music Recommendations with Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

The aim of this research is to investigate the development and performance evaluation of a music recommendation classification system that uses various machine learning models. The models under the consideration are Random Forest, Decision Tree, Gradient Boosting, Support Vector Machine (SVM), and Recurrent Neural Network (RNN). The purpose of this study is to evaluate the performance of these models in suggesting music in three distinct scenarios: the explicitness of the song, mode-based preferences, and the popularity of the song. The experiment is based on using extensive large datasets that are customized to recognize and capture the particular aspects of user preferences and behavior. A dataset containing detailed song attributes is used to train the models for explicit song recommendations. In the mode-based scenario, the focus is on understanding user preferences in accordance with the musical mode of the songs. Additionally, popularity is included to assess the models’ ability to recommend music according to prevailing trends. A comprehensive overview of the models’ performance is provided by the evaluation metrics used, which include accuracy, precision, recall, and F1 score. The results highlight the strengths and weaknesses of each model under different recommendation scenarios. Furthermore, the report describes the findings gained during the experimentation process, shedding light on the factors that influence the effectiveness of machine learning models in the music recommendation field. The research is valuable in providing guidance on selecting appropriate models for specific recommendation contexts in the field of music recommendation systems. The findings demonstrate the value of adjusting machine learning methods to user preferences, and provide a basis for future progress in personalized music recommendation systems.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Rustam, Furqan UNSPECIFIED
Uncontrolled Keywords:	Music Recommendation System; Machine learning Models
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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Music Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	15 May 2025 15:24
Last Modified:	15 May 2025 15:24
URI:	https://norma.ncirl.ie/id/eprint/7552

Actions (login required)

View Item