The advancement of generative AI has given rise to pressing copyright challenges, particularly in music industry. This paper focuses on the economic aspects of these challenges, emphasizing that the economic impact constitutes a central issue in the copyright arena. The complexity of the black-box generative AI technologies not only suggests but necessitates algorithmic solutions. However, such solutions have been largely missing, leading to regulatory challenges in this landscape. We aim to bridge the gap in current approaches by proposing potential royalty models for revenue sharing on AI music generation platforms. Our methodology involves a detailed analysis of existing royalty models in platforms like Spotify and YouTube, and adapting these to the unique context of AI-generated music. A significant challenge we address is the attribution of AI-generated music to influential copyrighted content in the training data. To this end, we present algorithmic solutions employing data attribution techniques. Our experimental results verify the effectiveness of these solutions. This research represents a pioneering effort in integrating technical advancements with economic and legal considerations in the field of generative AI, offering a computational copyright solution for the challenges posed by the opaque nature of AI technologies.

Spotify's royalty model will get a massive revamp next year to give "working artists" a bigger cut, according to Music Business Worldwide. Starting in the first quarter of 2024, Spotify will reportedly implement three changes meant to "combat three drains on the royalty pool." The first one is establishing a minimum number of annual streams a track must reach before it starts generating royalties, which is supposed to demonetize tracks that earn less than 5 cents a month. Apparently, while these tracks make up a tiny percentage of music on the platform -- 99.5 percent of all monetized content will still be earning money after this change -- their royalties still cost Spotify tens of millions of dollars a year. Based on Music Business Worldwide's computations, a track has to generate 200 plays a year to be able to earn 5 cents.