Predicting musician success from early career collaboration structures

Abstract
This work investigates whether early-career collaboration structures among musicians can predict long-term artistic success. Using MusicBrainz and Spotify data, we construct a large-scale collaboration network and model the generative processes underlying tie formation using Exponential Random Graph Models (ERGMs). We show that structural tendencies such as triadic closure, homophily, and productivity-driven exposure shape early collaboration, while weak ties are underrepresented relative to structural expectations. Using these insights, we engineer interpretable features and learned graph embeddings to predict long-term success, measured by Spotify follower count. Our findings demonstrate that early-network connectivity—particularly weak ties, cross-community bridging, and deviations from expected structural patterns—adds predictive signal beyond metadata baselines.
Similar content being viewed by others
Funding
This research received no external funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/
About this article
Cite this article
Woodburn, K., Frey, C., Petterson, C. et al. Predicting musician success from early career collaboration structures. Appl Netw Sci (2026). https://doi.org/10.1007/s41109-026-00823-1
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s41109-026-00823-1

The study used MusicBrainz and Spotify data to construct a collaboration network. Exponential Random Graph Models (ERGMs) modeled tie formation processes. Structural tendencies identified include triadic closure, homophily, and productivity-driven exposure. Weak ties were underrepresented compared to structural expectations. Interpretable features and graph embeddings were engineered to predict long-term success based on Spotify follower count.

Early-career collaboration structures among musicians are investigated to determine their predictive power regarding long-term artistic success, measured by Spotify follower count. The research constructs a large-scale collaboration network using MusicBrainz and Spotify data. Exponential Random Graph Models (ERGMs) are used to model the generative processes that lead to tie formation within this network. The analysis reveals that structural tendencies like triadic closure, homophily, and productivity-driven exposure shape early collaborations. Furthermore, weak ties are found to be underrepresented relative to expected structural patterns. The study engineers features and learned graph embeddings from these insights to predict long-term success.

The analysis suggests that the simple presence of collaborative connections is insufficient for predicting enduring artistic success; the structure of those connections matters significantly. The finding that weak ties are underrepresented relative to structural expectations points to a potential systemic bias in how collaboration forms, suggesting that long-term success may depend not just on dense community ties but also on bridging opportunities. This implies that artists who successfully navigate their careers may have leveraged cross-community bridging—connections between different musical spheres—rather than remaining solely within homogenous groups. The focus shifts from simply quantifying collaboration to understanding the *quality* and *type* of network architecture that supports sustained growth, suggesting that predictive signals exist in deviations from idealized structural patterns. This raises questions about whether success is an emergent property of structural dynamics or if external factors masked by metadata alone are being ignored. What mechanisms cause this underrepresentation of weak ties to persist across the artistic ecosystem? What specific types of cross-community bridging yield the most significant positive long-term correlation with follower growth?

Predicting musician success from early career collaboration structures

Facts Only

Executive Summary

Full Take

Sentinel — Human

Predicting musician success from early career collaboration structures

Facts Only

Executive Summary

Full Take

Sentinel — Human