This project is part of the coursework for CSE 144, an Applied Machine Learning class at the University of California, Santa Cruz, during the Spring 2024 quarter. Our objective is to develop a Spotify music suggestion model using a multimodal fusion-based attentive network that leverages multiple modalities, including tags, lyrics, and acoustic content of songs.
To get started with the project, follow these steps:
-
Clone the repository to your local machine:
git clone git@github.com:Ernesto2004/spotify_music_suggestion.git -
Navigate to the project directory and install the required dependencies:
pip install -r requirements.txt -
Create a folder named
miscin the project directory. This folder will be used to store the dataset. -
Download the dataset from the following link: Dataset Download Link
The dataset for this project is stored in the misc folder. It contains the necessary data for training and evaluating the Spotify music suggestion model.
The project relies on various Python libraries for data processing, model training, and evaluation. These dependencies are listed in the requirements.txt file and can be installed using pip.
Throughout this 10-week project, we experimented with different approaches which are documented and implemented in different branches which you can view here.
- Ernest Sarajyan
- Cameron Hall
- Eesha Krishnamagaru
- Josue Martinez
- Miguel Mascareno