Article Details

Abstract

With the popularity of internet music services, how to accurately recommend music for users has become an important research topic. This paper aims at the shortcomings of the existing music recommendation system in dealing with problems such as cold-start and data sparsity. A music recommendation algorithm based on Non-Negative Matrix Factorization (NMF) is proposed. The study uses a dataset from a collaboration project with NetEase Cloud Music, which contains more than 57 million music interaction records of more than 2 million users. By introducing user behavior weights and sparse constraints, weighted NMF and sparse NMF models are constructed respectively. The experimental results show that the weighted NMF performs best when dealing with high-frequency interactive users, and the F1 score reaches 0.997 6. The sparse NMF has more advantages in dealing with cold-start users. For users with fewer than 10 interactions, the recommendation accuracy is 15% higher than that of the basic NMF. The research results provide new solutions for the optimization of the music recommendation system.

Keywords

Machine Learning; music recommendation model; NMF

References

1. [1] BOBADILLA J，ORTEGA F，HERNANDO A，et al. Recommender Systems Survey [J]. Knowledge-Based Systems，2013，46：109-132.
2. [2] SHI Y，LARSON M，HANJALIC A. Collaborative Filtering Beyond the User-Item Matrix: A Survey of the State of the Art and Future Challenges [J].ACM Computing Surveys (CSUR)，2014，47（1）：1-45.
3. [3] VARGHESE K，M KOLHEKAR M M，HANDE S. Denoising of Facial Images Using Non-Negative Matrix Factorization with Sparseness Constraint [C]//2018 3rd International Conference for Convergence in Technology (I2CT).Pune：IEEE，2004：1-4.
4. [4] RICCI F，ROKACH L，SHAPIRA B，et al. Recommender Systems Handbook [M].New York：Springer，2011.
5. [5] KOREN Y，BELL R，VOLINSKY C. Matrix Factorization Techniques for Recommender Systems [J].Computer，2009，42（8）：30-37.
6. [6] SU X Y，KHOSHGOFTAAR T M. A Survey of Collaborative Filtering Techniques [J].Advances in Artificial Intelligence，2009，2009（1）：1-19.
7. [7] SCHAFER J B，KONSTAN J A，RIEDL J. E-Commerce Recommendation Applications [J].Data Mining and Knowledge Discovery，2001，5（1）：115-153.
8. [8] ZHANG S，YAO L，SUN A，et al. Deep Learning Based Recommender System: A Survey and New Perspectives [J].ACM Computing Surveys，2019，52（1）：5.1-5.38.
9. [9] KIM J，PARK H. Fast Nonnegative Matrix Factorization: An Active-Set-Like Method and Comparisons [J].SIAM Journal on Scientific Computing，2011，36（6）：3261-3281.
10. [10] MNIH A，SALAKHUTDINOV R R. Probabilistic Matrix Factorization [C]//Advances in Neural Information Processing Systems 15: Proceedings of the 2002 Conference.Vancouver：MIT Press，2003：1-7.
11. [11] HU Y F，KOREN Y，VOLINSKY C. Collaborative Filtering for Implicit Feedback Datasets [C]//2008 Eighth IEEE International Conference on Data Mining.Pisa：IEEE，2008：263-272.
12. [12] ZENG W，FAN G，SUN S，et al. Collaborative Filtering Via Multi-Layer Neural Networks [J/OL].Applied Soft Computing，2021，109：107516[2024-10-05].https://doi.org/10.1016/j.asoc.2021.107516.
13. [13] FANG H，LI A，XU H X，et al. Sparsity-Constrained Deep Nonnegative Matrix Factorization for Hyperspectral Unmixing [J].IEEE Geoscience and Remote Sensing Letters，2018，15（7）：1105-1109.
14. [14] GUO Z X，ZHANG S H. Sparse Deep Nonnegative Matrix Factorization [J/OL].arXiv:1707.09316 [cs.CV].[2024-09-26].https://doi.org/10.48550/arXiv.1707.09316.

About the authors

Jinlong (2000-), male, Han ethnicity, from Guangyuan, Sichuan, currently pursuing a master's degree in data science and machine learning.