Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{193075,
        author = {Dr. Vaishnavi J. Deshmukh and Aditya Bahe and Adarsh Bhankhede and Harshal Harne and Rohan Thakare and Ayush Wade},
        title = {Music Recommendation System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {3590-3596},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193075},
        abstract = {The music industry has seen explosive growth, with hundreds of millions of users streaming content worldwide. Personalized recommendation systems are therefore crucial to help listeners navigate vast music libraries efficiently. This project develops a Music Recommendation System that takes a user-input song and suggests similar tracks based on audio features and metadata. We implement a three-tier architecture: an HTML/CSS frontend for input, a Python/Flask backend for processing, and a CSV dataset of song features. The recommendation logic uses clustering of song feature vectors and similarity measures to identify songs related to the input. For example, our system clusters songs using k-means and returns top–k similar songs within the same cluster. Evaluation on sample data indicates high recommendation accuracy (comparable to published systems achieving over 87% accuracy). In test cases with known songs, the system successfully retrieved relevant recommendations. The results suggest that even a simple hybrid approach can yield effective personalization. In conclusion, our Music Recommendation System demonstrates the feasibility of content-based recommendations and achieves strong performance on benchmark metrics. Future work will incorporate user behavior data and advanced models to further improve accuracy.},
        keywords = {music recommendation; content-based filtering; collaborative filtering; deep},
        month = {February},
        }