TL;DR Getting a response from GenAI is quick and straightforward. But what about the confidence level for that response? In [...]
Published by Molly Zhu (Senior Engineering Manager), Xin Xu (Senior ML Engineer), and Kathy Gao (Senior Data Scientist)
On Spotify’s Analytics Platform, we’re dedicated to building products that empower data practitioners to discover, analyze, and share insights — [...]
Published by Federica Luraschi, Senior Data Scientist, with co-author Serena Fang
We have a lot of dashboards at Spotify. Our Insight teams and analysts from across the company are constantly whipping [...]
Published by Skyler Johnson, Senior Data Scientist
Check out Data Platform Explained Part I, where we started sharing the journey of building a data platform, its building [...]
Published by Anastasia Khlebnikova (Senior Engineer) and Carol Cunha (Product Manager)
TL;DR Sometimes we cannot estimate the required sample size needed to power an experiment before starting it. To alleviate this [...]
Published by Mårten Schultzberg, Sr. Manager, Staff Data Scientist
As engineers working at Spotify, we frequently find ourselves explaining our robust data platform to fellow professionals who are contemplating [...]
Published by Anastasia Khlebnikova (Senior Engineer) and Carol Cunha (Product Manager)
TL;DR We summarize the findings in our recent paper, Schultzberg, Ankargren, and Frånberg (2024), where we explain how Spotify’s decision-making [...]
Published by Mårten Schultzberg (Sr. Manager, Staff Data Scientist), Sebastian Ankargren (Sr. Data Scientist), and Mattias Frånberg (Sr. Data Scientist)
Large sets of diverse data present several challenges for clustering, but through a novel approach that combines dimensionality reduction, recursion, and supervised machine learning, we’ve been able to obtain strong results.
Published by Gustavo Pereira, Sr. Data Scientist
For the past decade, Spotify has used approximate nearest-neighbor search technology to power our personalization, recommendation, and search systems. These [...]
Published by Peter Sobot, Staff ML Engineer
What is “Exclude from your taste profile”? Are you a parent forced to put the Bluey theme song on repeat? [...]
Published by Mark Koh, Senior ML Engineer
When we want to determine the causal effect of a product or business change at Spotify, A/B testing is the [...]
Published by Bradley Doll (Insights Manager), Jeffrey Li (Insights Manager), and Tolga Oztan (Sr. Data Scientist)
At Spotify, we run a lot of A/B tests. Most of these tests follow a standard design, where we assign [...]
Published by Benjamin Elbers, Data Scientist
As companies mature, it’s easy to believe that the core experience and most user needs have been resolved, and all [...]
Published by Gabriella Ljunggren, Data Scientist
TL;DR: Spotify is releasing a new commercial product for software development teams: a version of our homegrown experimentation platform that [...]
Published by Tyson Singer, Head of Technology and Platforms
In Part 1 of this series, we introduced the within-unit peeking problem that we call the “peeking problem 2.0”. We [...]
Published by Sebastian Ankargren (Sr. Data Scientist), Mattias Frånberg (Sr. Data Scientist), and Mårten Schultzberg (Sr. Manager/Staff Data Scientist)
Spotify’s approach to challenges in sequential testing with longitudinal data At Spotify, we’re constantly improving our data infrastructure, which means [...]
Published by Sebastian Ankargren (Sr. Data Scientist), Mattias Frånberg (Sr. Data Scientist), and Mårten Schultzberg (Sr. Manager/Staff Data Scientist)
Messaging at Spotify At Spotify, we use messaging to communicate with our listeners all over the world. Our Messaging team [...]
Published by Euan Dowers, Senior ML Engineer
In the fast-paced world of streaming, personalization plays a vital role in enhancing user experiences. At Spotify, our Home serves [...]
Published by Nik Goyle, Product Manager
TL;DR Sequential tests are the bread and butter for any company conducting online experiments. The literature on sequential testing has [...]
Published by Mårten Schultzberg (Staff Data Scientist) and Sebastian Ankargren (Sr. Data Scientist)
We did a couple of new things in Wrapped this year, and one of these is a thing called Your [...]
Published by glenn mcdonald, Data Alchemy
TL;DR: Using the properties of the Poisson bootstrap algorithm and quantile estimators, we have been able to reduce the computational [...]
Published by Mårten Schultzberg (Senior Data Scientist) and Sebastian Ankargren (Data Scientist)
At Spotify, we aim to build and improve our product in a data-informed way. To do that, teams are encouraged [...]
Published by Claire Detilleux, Sr. Data Scientist
At Spotify, data rules all. We log a variety of data, from listening history, to results of A/B testing, to [...]
Published by Flavio Santos (Data Infrastructure Engineer) and Robert Stephenson (Senior Product Manager)
At Spotify we run hundreds of experiments at any given time. Coordinating these experiments, i.e., making sure the right user [...]
Published by Mårten Schultzberg, Oskar Kjellin, and Johan Rydberg
