As Internet industry constantly develops and the computer penetration rate continues to grow, the number of online music platforms and music users has been able to increase year by year. With that comes more music choices, information overload has become a very prominent problem. Therefore, how to make users choose their favorite music more conveniently is one of the most challenging problems faced by online music recommendation systems. This paper bases on the existing recommendation system research and uses the collaborative filtering algorithm, proposes a music recommendation method from three perspectives: user attributes, music types and time migration. It is found that the online music recommendation from these three perspectives has a good effect, which can provide a reference for the construction of the current online music recommendation system and is also helpful to platform management practice.
Li, Yixi; Liu, Mandie; He, Fu; and Li, Liangqiang, "Personalized Music Recommendation Based on Style Type" (2020). ICEB 2020 Proceedings (Hong Kong, SAR China). 27.