Summary of Conditional Quantile Estimation For Uncertain Watch Time in Short-video Recommendation, by Chengzhi Lin et al.
Conditional Quantile Estimation for Uncertain Watch Time in Short-Video Recommendation
by Chengzhi Lin, Shuchang Liu, Chuyuan Wang, Yongqi Liu
First submitted to arxiv on: 17 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The Conditional Quantile Estimation (CQE) framework is a machine learning approach that models the entire conditional distribution of watch time for each user-video pair, providing a flexible and comprehensive understanding of user behavior. This method uses quantile regression to characterize the complex watch-time distribution, allowing for better prediction of watch time and improved recommendation systems. The authors demonstrate the effectiveness of CQE through offline experiments and online A/B tests, showing significant improvements in key evaluation metrics such as active days, active users, engagement duration, and video view counts. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps us understand how people watch short videos on platforms like KuaiShow. It’s hard to predict how long someone will watch a video because different people have different ways of engaging with videos. The authors came up with a new way to estimate this called Conditional Quantile Estimation (CQE). They used this method to improve the recommendation system on KuaiShow, which made users more engaged and watched more videos. This is important for making sure that people have a good experience when using these platforms. |
Keywords
» Artificial intelligence » Machine learning » Regression
