Bayesian Negative Binomial Regression of Afrobeats Chart Persistence

TL;DR

This study assesses whether collaborations extend Afrobeats songs' persistence on the Nigeria Spotify Top 200 in 2024 after accounting for overall popularity. It employs a Bayesian Generalized Linear Model with a Negative Binomial likelihood, modeling the track-level count of days on chart $n_i$ as a function of collaboration status and log total streams $x_{i,\text{logStreams}}$, with inference via MCMC in PyMC. The key finding is a small, robust negative collaboration effect: $\exp(\beta_1) \approx 0.93$ (95% CI $[0.88,0.99]$) and $P(\beta_1>0|\cdot) \approx 0.007$, indicating that, at a fixed level of popularity, collaborations are associated with about 7% fewer days on the chart. The work demonstrates a full Bayesian workflow for overdispersed count data in streaming contexts and highlights the importance of controlling for popularity when evaluating collaboration effects on chart persistence.

Abstract

Afrobeats songs compete for attention on streaming platforms, where chart visibility can influence both revenue and cultural impact. This paper examines whether collaborations help songs remain on the charts longer, using daily Nigeria Spotify Top 200 data from 2024. Each track is summarized by the number of days it appears in the Top 200 during the year and its total annual streams in Nigeria. A Bayesian negative binomial regression is applied, with days on chart as the outcome and collaboration status (solo versus multi-artist) and log total streams as predictors. This approach is well suited for overdispersed count data and allows the effect of collaboration to be interpreted while controlling for overall popularity. Posterior inference is conducted using Markov chain Monte Carlo, and results are assessed using rate ratios, posterior probabilities, and predictive checks. The findings indicate that, after accounting for total streams, collaboration tracks tend to spend slightly fewer days on the chart than comparable solo tracks.

Figures (1)

• Figure 1: Posterior predictive check for days on chart. The solid line represents the empirical density of $n_i$, while the shaded region shows the distribution of posterior predictive replicates $n_i^{\text{rep}}$.