Best Practices for Top-N Recommendation Evaluation: Candidate Set Sampling and Statistical Inference Techniques
Conference on Information and Knowledge Management(2022)
摘要
ABSTRACTTop-N recommendation evaluation experiments are complex, with many decisions needed. These decisions are often made inconsistently, and we don't have clear best practices for many of them. The goal of this project, is to identify, substantiate, and document best practices to improve evaluations.
更多查看译文
关键词
recommender systems, offline evaluation, statistical inference, candidate set sampling
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要