Mathematical Modeling and Forecasting of Music Popularity: an Overview of Approaches and Methods
DOI:
https://doi.org/10.36683/ee244.4-13Keywords:
music industry, time series analysis, streaming platforms, regression models, survival models, Poisson process, Lotka-Volterra system, LSTM-RPA, playlist influence, genre competitionAbstract
The article presents a comprehensive review of modern methods of study of musical compositions popularity, including statistical, temporal and connectionist approaches. Regression models with fixed effects, survival models, nonstationary Poisson processes and systems of Lotka-Volterra equations, as well as STL decomposition algorithms and neural networks (LSTM-RPA) are considered. Their advantages and limitations in analyzing the dynamics of listening, the influence of playlists and competitive interaction of genres are discussed. The main attention is paid to the analysis of their advantages and disadvantages in the context of the tasks set - forecasting long-term changes in the popularity of compositions, assessing the impact of playlists and the dynamics of genre competition. On the basis of the analysis, the author concludes that the use of LSTM-RPA models is the most effective for forecasting due to their ability to minimize errors accumulation. The author contribution is in proposition of a new approach: the adaptation of hybrid methodology combining neural network models and time series for taking into account contextual factors such as influence of social trends and marketing activity that can significantly increase the versatility and accuracy of the forecasts.Downloads
References
Wikström, P. The music industry: music in the cloud : Digital media and society series. The music industry / P. Wikström. – Cambridge ; Malden, MA : Polity, 2009. – 204 p.
IFPI Global Music Report 2024 // IFPI, 2024. – URL: https://ifpi-website-cms.s3.eu-west-2.amazonaws.com/IFPI_GMR_2024_State_of_the_Industry_db92a1c9c1.pdf.
Vaccaro, V. L. The Evolution of Business Models and Marketing Strategies in the Music Industry / V. L. Vaccaro, D. Y. Cohn // International Journal on Media Management. – 2004. – Vol. 6, Issue 1-2. – P. 46-58. – DOI 10.1080/14241277.2004.9669381.
McKenzie, J. Digital piracy / J. McKenzie. // Handbook of Cultural Economics, Third Edition / eds. R. Towse, T. Navarrete Hernández. – Edward Elgar Publishing, 2020. – DOI 10.4337/9781788975803.00031.
Farchy, J. D. Artificial intelligence / J. Farchy, J. Denis // Handbook of Cultural Economics, Third Edition / eds. R. Towse, T. Navarrete Hernández. – Edward Elgar Publishing, 2020. – DOI 10.4337/9781788975803.00010.
Grote, F. Mark Mulligan: Awakening. The Music Industry in the Digital Age. London (MIDiA Research) 2015, 332 Seiten / F. Grote. // Zeitschrift für Kulturmanagement. – 2016. – Vol. 2. – P. 177-182. – DOI 10.14361/zkmm-2016-0214.
Aguiar, L. Platforms, Power, and Promotion: Evidence from Spotify Playlists / L. Aguiar, J. Waldfogel // The Journal of Industrial Economics. – 2021. – Vol. 69, Issue 3. – P. 653-691. – DOI 10.1111/joie.12263.
Hirsch. The Structure of the Popular Music Industry: The Filtering Process by which Records are Preselected for Public Consumption / Hirsch // Institute for Social Research, The University of Michigan. – 1973.
Ordanini, A. Selection models in the music industry: How a prior independent experience may affect chart success / A. Ordanini // Journal of Cultural Economics. – 2006. – Vol. 30. – P. 183-200. – DOI 10.1007/s10824-006-9013-8.
Morris, J. W. Control, curation and musical experience in streaming music services / J. W. Morris, D. Powers // Creative Industries Journal. – 2015. – Vol. 8, Issue 2. – P. 106-122. – DOI10.1080/17510694.2015.1090222.
Analyzing the Spotify Top 200 Through a Point Process Lens / M. Harris, B. Liu, C. Park [et al.] // arXiv. – 2019. – DOI 10.48550/arXiv.1910.01445.
Kaimann, D. “I will survive”: Online streaming and the chart survival of music tracks / D. Kaimann, I. Tanneberg, J. Cox. // Managerial and Decision Economics. – 2021. – Vol. 42, Issue 1. – P. 3- 20. – DOI 10.1002/mde.3226.
An application of the Lotka-Volterra model with time series analysis to forecast spotify streams of two genres / J. R. F. Padilla, E. D. Baniaga, R. C. Addawe, J. P. T. Viernes. // Proceedings of the International Conference on Mathematical Sciences and Technology 2022 (MATHTECH 2022): Navigating the Everchanging Norm with Mathematics and Technology. 13–15 September 2022 Penang, Malaysia, 2024. – P. 070001. – DOI 10.1063/5.0192499.
Music popular trends prediction based on time series / Yu W. [et al.] // Computer Engineering & Science. – 2018. – Vol. 40, Issue 9. – P. 1703-1709. (in Chinese.) – URL: http://joces.nudt.edu.cn/CN/abstract/abstract15746.shtml.
LSTM-RPA: A Simple but Effective Long Sequence Prediction Algorithm for Music Popularity Prediction. LSTM-RPA / K. Li, M. Li, Y. Li, M. Lin // arXiv. – 2021. – DOI: 10.48550/arXiv.2110.15790.
