Get the latest tech news

Music recommendation system using transformer models


Transformers in music recommendation August 16, 2024 Anushya Subbiah and Vikram Aggarwal, Software Engineers, Google Research We present a music recommendation ranking system that uses Transformer models to better understand the sequential nature of user actions based on the current user context. Quick links Users have more choices for listening to music than ever before.

When designing and deploying a ranking model, it is hard to manually select and apply relative weights to specific user actions out of the many hundreds or thousands that they may commonly take. Offline analysis and live experiments demonstrate that using this Transformer significantly improves the performance of the ranking model, leading to a reduction in skip-rate and an increase in time users spend listening to music. Thanks to colleagues Reza Mirghaderi, Li Yang, Chieh Lo, Jungkhun Byun, Gergo Varady, and Sally Goldman, for their collaboration on this effort.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of transformer models

transformer models

Related news:

News photo

Falcon Mamba 7B’s powerful new AI architecture offers alternative to transformer models

News photo

Etched looks to challenge Nvidia with an ASIC purpose-built for transformer models

News photo

Sohu – first specialized chip (ASIC) for transformer models