Summary of Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction, by Yi Wu et al.
Learned Ranking Function: From Short-term Behavior Predictions to Long-term User Satisfaction
by Yi Wu, Daryl Chang, Jennifer She, Zhe Zhao, Li Wei, Lukasz Heldt
First submitted to arxiv on: 12 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
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 A machine learning system, known as the Learned Ranking Function (LRF), is introduced to optimize long-term user satisfaction by generating personalized recommendations based on short-term user-item behavior predictions. Unlike traditional approaches that rely on heuristic functions and hyperparameter tuning, LRF directly models the slate optimization problem to maximize user satisfaction. The proposed method employs a novel constraint optimization algorithm to stabilize trade-offs in multi-objective optimization. The effectiveness of LRF is evaluated through live experiments and its deployment on YouTube is described. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The Learned Ranking Function (LRF) is a new way to give people recommendations that they’ll really like in the long run. Right now, most recommendation systems use old rules and adjust some numbers to try to make people happy. But LRF tries to solve this problem directly by finding the best combination of items that will keep users satisfied over time. To do this, LRF uses a special algorithm that balances different goals and makes sure they don’t conflict with each other. The system was tested in real-life experiments and was even used on YouTube to make recommendations. |
Keywords
» Artificial intelligence » Hyperparameter » Machine learning » Optimization
