Beyond Relevance: Improving User Engagement by Personalization for Short-Video Search

TL;DR

This paper introduces $ ext{PR}^2$, a comprehensive personalization system for short-video search that significantly enhances user engagement by leveraging collaborative filtering, dense retrieval, and user preference modeling.

Contribution

The paper presents $ ext{PR}^2$, a novel personalized search framework combining multiple techniques, and demonstrates its effectiveness through deployment in a real-world short-video platform.

Findings

10.2% increase in CTR@10

20% increase in video watch time

1.6% uplift in search DAU

Abstract

Personalized search has been extensively studied in various applications, including web search, e-commerce, social networks, etc. With the soaring popularity of short-video platforms, exemplified by TikTok and Kuaishou, the question arises: can personalization elevate the realm of short-video search, and if so, which techniques hold the key? In this work, we introduce $\text{PR}^2$, a novel and comprehensive solution for personalizing short-video search, where $\text{PR}^2$ stands for the Personalized Retrieval and Ranking augmented search system. Specifically, $\text{PR}^2$ leverages query-relevant collaborative filtering and personalized dense retrieval to extract relevant and individually tailored content from a large-scale video corpus. Furthermore, it utilizes the QIN (Query-Dominate User Interest Network) ranking model, to effectively harness user long-term preferences and real-time behaviors, and efficiently learn from user various implicit feedback through a multi-task learning framework. By deploying the $\text{PR}^2$ in production system, we have achieved the most remarkable user engagement improvements in recent years: a 10.2% increase in CTR@10, a notable 20% surge in video watch time, and a 1.6% uplift of search DAU. We believe the practical insights presented in this work are valuable especially for building and improving personalized search systems for the short video platforms.