If algorithmic playlists aren’t triggered by scale or engagement thresholds, how should artists and labels evaluate performance? In Part II of our algorithmic optimization series, we introduce Music Tomorrow’s audit framework for measuring algorithmic positioning and growth potential. By analyzing audience clusters, addressable opportunity, exposure-to-feedback conversion, and scene-level momentum, we show how algorithmic visibility can be transformed from opaque stream counts into a structured investment decision system.

Why do some tracks trigger Discover Weekly or Release Radar while others stall — even after strong playlisting or early traction? In this article, we unpack the most common misconceptions about Spotify’s algorithmic playlists and explain why popularity thresholds, engagement benchmarks, and broad exposure strategies often fail to produce sustained recommendation support. Drawing on large-scale audit data, we show how modern recommender systems evaluate context, audience alignment, and signal clarity — and why algorithmic visibility is ultimately a question of positioning, not scale.

As streaming platforms increasingly mediate cultural exposure, understanding their impact on local music has become a policy concern. This case study examines how recommendation systems influence the visibility of francophone repertoire in France and Canada, revealing how language and market context shape algorithmic fairness and cultural representation.

What happens when you start talking to the recommender system? We put Spotify’s AI Playlists to the test to understand their real impact on discovery — and what they mean for artists and labels.

A deep dive into how fairness and transparency are reshaping music recommender systems — and how Music Tomorrow helps make algorithms more explainable.

Two years ago, we started developing our own platform, based on our knowledge about music recommender systems, to help labels make their artists more visible. Since then, we made significant advancements: you can now use our analytics tools to gain insights into how Spotify's algorithms perceive your music, and use this information to amplify your online presence. We collaborated with both major and independent industry players, including Universal Music Group, Warner Music, Handwritten Records, Tôt ou Tard, Because Music, among others, to fine-tune our tools and data, ensuring they meet the evolving needs of artists and labels alike.

In the second part in our series on RSO we present a framework for algorithmic optimization on DSPs (and, specifically, Spotify). Learn how you can manage the inputs processed by the recommender to amplify algorithmic traffic and discoverability of your catalog.

This is the first part in our series on algorithmic optimization on streaming platforms or simply RSO (for Recommender System Optimization). In this introductory piece, we will cover Music Tomorrow’s approach to algorithmic optimization and present the data tool we’ve developed that allows us to extract and analyze artists’ algorithmic profiles on Spotify.

Check out the most complete and up-to-date guide to Spotify recommendation algorithm, sourced by years of experience working in music RecSys.

Spotify's Discovery Mode: another nail in the streaming economy's coffin, or a long-awaited DSP ad tool for artists? Here's our take on it.

How fair music recommendation algorithms actually are? And what we could do to build more diverse music recommender systems? Let's find out!