Reproduce “You Know What You Will Like: People Predict Their Own Ratings Better Than Recommender Systems” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zihan Chen, Lei Nico Zheng, Di Zhu
The authors compare members’ expected ratings for unseen movies with their later ratings and recommender forecasts on MovieLens. Among 551 pairs from 277 members, guesses correlated 0.69 with later ratings, versus 0.59 for the strongest trained recommender, and ordered ratings correctly 72% of the time, versus 56% for MovieLens. However, 98.8% of prompts went unanswered, limiting findings to selected guesses later rated.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.