Publisher

UIMUIM

Journal UIM | Zeta - Math JournalUIM | Zeta - Math Journal Abstract

In the digital era, music streaming platforms face challenges in providing relevant music recommendations to users. This research aims to develop a music artist recommendation system based on the users listening history using the SVD and MICE methods. In this research, MICE was applied together with ALS predictive model. SVD is used to identify latent patterns between users and artists, while MICE address the problem of missing data in listening history. The data used comes from the online music platform Last.fm. Analysis was carried out with Julia 1.8.5 software. The results show that the model with MICE provides more accurate and consistent recommendations compared to SVD, especially in the context of missing data. Accuracy using the MICE model provides results of up to 96%, while the SVD model provides an accuracy of 90,22%. This approach can increase the relevance of recommendations, helping users find artists according to their preferences. These findings support the application of MICE in music recommendation systems, with the potential to improve user experience on music streaming platforms.

Conclusion

This research demonstrates that both SVD and MICE models exhibit good accuracy in modeling a recommendation system.The MICE model, achieving an accuracy of 96%, provides more accurate and consistent results than the SVD model, which has an accuracy of 90.This indicates that MICE effectively addresses missing data issues, leading to more relevant and personalized recommendations.These findings support the potential application of both methods in music recommendation systems facing missing data challenges, ultimately enhancing user experience.

Future Research

Further research could explore the integration of hybrid recommendation approaches, combining collaborative filtering with content-based filtering to leverage both user behavior and artist characteristics for more nuanced recommendations. Investigating the impact of different imputation techniques beyond MICE, such as deep learning-based imputation methods, could potentially improve accuracy in handling missing data. Additionally, a study focusing on the dynamic nature of user preferences over time, incorporating temporal factors into the recommendation model, could lead to more adaptive and personalized music suggestions. These avenues of research promise to refine music recommendation systems, offering users a more enriching and tailored listening experience.

References

1. Music Artist Recommendation System Based on Listening History Using SVD and MICE Imputation Approaches... doi.org/10.31102/zeta.2025.10.1.70-80Music Artist Recommendation System Based on Listening History Using SVD and MICE Imputation Approaches doi 10 31102 zeta 2025 10 1 70 80
2. Jurnal Ilmu Komputer dan Sistem Informasi (JIKSI). pemetaan lahan singular value linear discriminant... journal.untar.ac.id/index.php/jiksi/article/view/28198Jurnal Ilmu Komputer dan Sistem Informasi JIKSI pemetaan lahan singular value linear discriminant journal untar ac index php jiksi article view 28198

Metadata

File size	710.33 KB
Pages	11
DMCA	Report