KuaiRand is an unbiased sequential recommendation dataset collected from the recommendation logs of the video-sharing mobile app, Kuaishou (快手). It is the first recommendation dataset with millions of intervened interactions of randomly exposed items inserted in the standard recommendation feeds!
Compared with other datasets with random exposure, KuaiRand has the following advantages:
-It is the first sequential recommendation dataset with millions of intervened interactions of randomly exposed items inserted in the standard recommendation feeds.
-It has the most comprehensive side information including explicit user IDs, interaction timestamps, and rich features for users and items.
-It has 15 policies with each catered for a special recommendation scenario in the Kuaishou App.
-We introduce 12 feedback signals (e.g., click, like, and view time) for each interaction to describe the user’s comprehensive feedback.
-Each user has thousands of historical interactions on average.
-It has three versions to support various research directions in recommendation.
Use case
Reinforcement learning-based optimization of the video feed in a mobile entertainment app (e.g., TikTok / Kuaishou)
| Example observation | User profile (age, gender, region) Sequential history of the last N videos (IDs, categories, creator, duration) Recent feedback (watch time, like, follow, comment) Timestamp |
| Example actions | Proposed video ID (among ~9M items). (Can be restricted to a candidate slate (~100) provided in the dataset) |
| Example reward | watch_time + 5*is_like + 10*is_share + 15*is_follow |