Sep 18, 2025
Calibrated Recommendations with Contextual Bandits on Spotify Homepage
Streaming platforms typically offer a wide variety of content types...
Sep 18, 2025
Generalized user representations for large-scale recommendations
Personalization lies at the heart of the Spotify platform...
Sep 17, 2025
You Say Search, I Say Recs: A Scalable Agentic Approach to Query Understanding and Exploratory Search at Spotify
Personalized recommendations are at the heart of Spotify’s experience...
Sep 16, 2025
AudioBoost: Increasing Audiobook Retrievability in Spotify Search with Synthetic Query Generation
Spotify has recently introduced audiobooks as part of its catalog...
Sep 11, 2025
Beyond the Next Track: Spotify Research at RecSys 2025
At Spotify, we believe recommendation is about more than simply choosing the next track...
Sep 3, 2025
Optimizing Budget Allocation with Theoretical Guarantees and Adaptive Learning
Online platforms, whether for entertainment or other personalized experiences...
Aug 21, 2025
Scaling Transformer-based Text-to-Speech with Knowledge Distillation
Transformer-based models have led to dramatic improvements in text-to-speech (TTS) quality...
Aug 7, 2025
ForTune: Running Offline Scenarios to Estimate Impact on Business Metrics
For product leaders at Spotify and other web-facing companies, making informed decisions about...
Aug 5, 2025
Modality-aware Multi-task Learning to Optimize Ad Targeting at Scale
Much of our on-platform listening happens while users are occupied with something else...
Jul 25, 2025
Optimizing Query Expansions via LLM Preference Alignment
One of the longstanding challenges in information retrieval is the vocabulary mismatch problem...
Jul 22, 2025
Local Interference: Removing Interference Bias in Semi-Parametric Causal Models
Causal inference helps us answer “what-if” questions—what would happen if we recommended a podcast instead..
Jul 22, 2025
The Hardness of Validating Observational Studies with Experimental Data
Many models at Spotify are trained using randomized data to prevent bias...