VK-LSVD: A Large-Scale Industrial Dataset for Short-Video Recommendation

TL;DR

This paper introduces VK-LSVD, the largest open industrial dataset for short-video recommendation, enabling research on modeling rapid user interest shifts with real-world data.

Contribution

The paper presents VK-LSVD, a large-scale, real-world dataset for short-video recommendation, filling a critical gap in available data for research and benchmarking.

Findings

Supports research in sequential recommendation and cold-start scenarios.

Used in VK RecSys Challenge 2025 to advance recommender system development.

Provides rich features and diverse feedback signals for comprehensive analysis.

Abstract

Short-video recommendation presents unique challenges, such as modeling rapid user interest shifts from implicit feedback, but progress is constrained by a lack of large-scale open datasets that reflect real-world platform dynamics. To bridge this gap, we introduce the VK Large Short-Video Dataset (VK-LSVD), the largest publicly available industrial dataset of its kind. VK-LSVD offers an unprecedented scale of over 40 billion interactions from 10 million users and almost 20 million videos over six months, alongside rich features including content embeddings, diverse feedback signals, and contextual metadata. Our analysis supports the dataset's quality and diversity. The dataset's immediate impact is confirmed by its central role in the live VK RecSys Challenge 2025. VK-LSVD provides a vital, open dataset to use in building realistic benchmarks to accelerate research in sequential recommendation, cold-start scenarios, and next-generation recommender systems.