Reproduce “A Survey of Retrieval Algorithms in Ad and Content Recommendation 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
Yu Zhao, Fang Liu
The survey explains how two-tower retrieval matches users with items while distinguishing advertising's goals of engagement, conversions, and revenue from organic recommendations' goals of user experience and retention. It describes separate user and item encoders whose representations are compared, with item vectors precomputed for indexing. The paper reports no benchmark; data quality, privacy, and cold-start remain challenges.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.