Spotify VO ML Depth

Sequential Playlist Recommendation
ML Depth Interview
We are building a model that generates personalized playlists intended to power. a new feature in Spotify that offers users dynamically generated playlists based on their listening habits and the current context.
Product Objective
We want an ML model that, given a user and request context, generates a 10-track playlist from a candidate pool of 10,000 tracks.
The

您好！
本帖隐藏的内容需要积分高于 188 才可浏览
您当前积分为 0。
使用VIP即刻解锁阅读权限或查看其他获取积分的方式

游客，您好！
本帖隐藏的内容需要积分高于 188 才可浏览
您当前积分为 0。
VIP即刻解锁阅读权限 或 查看其他获取积分的方式
Unlock interview details and practice with AI
Curated Interview Questions from Top Companies

al popularity stats.
Request-Level Features
Time of day
Day of week.
Device type
Entry point (e.g., homepage, search, context menu)
User-Track Interaction Logs (28d time window)
Playback events, skips, replays
Add-to-playlist/add-to-library events
Implicit sequences of track plays (for playlist/session modeling)