Mining and Forecasting Career Trajectories of Music Artists

Abstract

Many musicians, from up-and-comers to established artists, rely heavily on performing live to promote and disseminate their music. To advertise live shows, artists often use concert discovery platforms that make it easier for their fans to track tour dates. In this paper, we ask whether digital traces of live performances generated on those platforms can be used to understand career trajectories of artists. First, we present a new dataset we constructed by crossreferencing data from such platforms. We then demonstrate how this dataset can be used to mine and predict important career milestones for the musicians, such as signing by a major music label, or performing at a certain venue. Finally, we perform a temporal analysis of the bipartite artist-venue graph, and demonstrate that high centrality on this graph is correlated with success.

A Model for Predicting Music Popularity on Streaming Platforms

“…Regarding the use of concert information to make predictions, Arakelyan et al [6] collected data from the SongKick website 7 . The data contained the location, list of participating artists, event name and a value indicating the event popularity given by the website.…”

“…Spotify was chosen as our study case because it is the world's second largest music streaming service in number of users. The first one is Soundcloud, which lacks songs from renowned artists and record labels 5,6 . We consider a music to be popular if it has been featured in the Spotify's Top 50 Global daily ranking, which contains the 50 songs with most listeners the day before each edition.…”

Variation across Scales: Measurement Fidelity under Twitter Data Sampling

“…No two entities within the same set are linked. Bipartite graphs have been used in many social applications, e.g., mining the relation between scholars and published papers (Newman 2001), or between artists and concert venues (Arakelyan et al 2018). Here we construct the user-hashtag bipartite graphs for both the complete and the sample sets.…”

Will I Remain Popular? A Study Case on Spotify

“…Em relação ao uso de dados de eventos para realização da previsão no mercado, destacamos o trabalho de [Arakelyan et al 2018]. Utilizando dados do site SongKick 8 , os autores coletaram informações sobre 645.507 concertos, incluindo a localização e nome do evento, a lista de artistas participantes e um valor em popularidade dado pela plataforma.…”

“…O problema de realizar predições no mercado musical vem sendo estudado na literatura, onde algoritmos de aprendizagem de máquina apresentam melhores resultados de forma geral. Dados de diferentes fontes foram utilizados para desenvolver modelos preditivos, como informações de redes sociais [Dhar and Chang 2009] [Shulman et al 2016], das características acústicas das faixas [Lee and Lee 2018] [Interiano et al 2018], de shows e festivais [Arakelyan et al 2018] [Steininger and Gatzemeier 2013] e de colaborações entre artistas [Silva et al 2019] [Araújo et al 2017]. Para o desenvolvimento de nosso modelo utilizamos duas abordagens com o intuito de identificar qual destas apresenta melhor resultado em nossos experimentos.…”