Reproduce “Recommendation Feedback Loops Shape Urban Income Segregation and Venue Visitation” 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
Guangyuan Weng, Lin Chen, Ciro Beneduce, Giovanni Mauro, Massimiliano Luca, Takahiro Yabe, Bruno Lepri, Luca Pappalardo and 1 more
The authors simulate restaurant recommendations as a feedback loop using GPS mobility data, fixed travel schedules, venue capacity constraints, and weekly retraining across four U.S. metropolitan areas. Higher offline accuracy aligns with higher segregation in all four areas; in Boston, UR-POI scores .322 on NDCG@20 and .353, versus .291 for observed visits. These are simulation results, not post-deployment outcomes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.