View Proposal
-
Proposer
-
Habte Lejebo Leka
-
Title
-
Personalized Music Recommendation System
-
Goal
-
-
Description
- The project aims to develop a system for generating personalized music recommendations based on user preferences and song characteristics. Students will analyse music and user-preference data, perform data preprocessing and feature engineering, and develop suitable recommendation approaches. The system will provide an interactive web interface that allows users to explore songs and artists, provide preferences or ratings, and receive personalized song or playlist recommendations. The project will evaluate the quality of the generated recommendations using appropriate evaluation measures.
- Resources
-
"Tegene, Abebe, Qiao Liu, Yanglei Gan, Tingting Dai, Habte Leka, and Melak Ayenew. ""Deep Learning and Embedding Based Latent Factor Model for Collaborative Recommender Systems."" Applied Sciences 13.2 (2023): 726. Dataset: Million Song Dataset
Kaggle Link: https://www.kaggle.com/datasets/bricevergnou/spotify-recommendation"
-
Background
-
-
Url
-
-
Difficulty Level
-
Moderate
-
Ethical Approval
-
None
-
Number Of Students
-
2
-
Supervisor
-
Habte Lejebo Leka
-
Keywords
-
recommender systems, music recommendation, personalized recommendation, machine learning, user preferences
-
Degrees
-
Bachelor of Science in Computational Sciences and Software Engineering