Recommendation Feedback Loops Shape Urban Income Segregation and Venue Visitation
Abstract
Location-based recommender systems shape where people go in cities and learn from the visits they steer, forming a human-AI feedback loop. This feedback loop shapes whom people share places with across income groups and which venues keep attracting customers. Yet platforms judge these systems by their offline accuracy on past visits, a test in which the suggestions never change where people go and which therefore cannot capture long-term effects. Studying these effects in cities is challenging because, unlike online resources, travel constraints and limited venue capacity shape where people can go, while each recommended visit also changes whom other visitors encounter. To capture such features, we build a long-term simulation framework based on fine-grained human mobility data from four U.S. metropolitan areas, with distance and capacity constraints. Focusing on food venues, we study two urban consequences: how unevenly people's exposure is distributed across income groups (experienced income segregation) and the share of venues receiving no visits from simulated residents (venue disappearance). We find that, under every algorithm and in every metropolitan area, at least a fifth of venues stop receiving visits, and that more than half of this loss arises from retraining. More importantly, more accurate algorithms leave people more segregated, and the most accurate algorithm leaves people 15-21% more segregated than they actually are. We then test a re-ranking intervention that favours less popular venues and runs on top of a platform's existing algorithm. It lowers both venue disappearance and segregation across algorithms, largely without directing people to venues where they may feel less comfortable. Our results suggest that impact assessments of recommender systems should account for the feedback loop and report segregation and venue disappearance beyond accuracy.
Related
- To collapse or not to collapse: Halo evolution with self-interacting dark matter mass segregation
- Clutter Noise Induced Phase Segregation in Binary Active Polar Flocks
- BanglaShop-CRS: A User-Centric Bangla Dataset for Conversational Recommendation
- Measuring Diversity and Segregation with Convex Functions
- Magnetic fields of current loops and charged particles around black holes in modified gravity
BibTeX
@misc{weng2026recommendation,
title = {{Recommendation Feedback Loops Shape Urban Income Segregation and Venue Visitation}},
author = {Guangyuan Weng and Lin Chen and Ciro Beneduce and Giovanni Mauro and Massimiliano Luca and Takahiro Yabe and Bruno Lepri and Luca Pappalardo and Esteban Moro},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.41911},
eprint = {2610.41911},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.41911},
}
RIS
TY - UNPB
TI - Recommendation Feedback Loops Shape Urban Income Segregation and Venue Visitation
AU - Guangyuan Weng
AU - Lin Chen
AU - Ciro Beneduce
AU - Giovanni Mauro
AU - Massimiliano Luca
AU - Takahiro Yabe
AU - Bruno Lepri
AU - Luca Pappalardo
AU - Esteban Moro
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2610.41911
UR - https://arxiv.org/abs/2610.41911
AB - Location-based recommender systems shape where people go in cities and learn from the visits they steer, forming a human-AI feedback loop. This feedback loop shapes whom people share places with across income groups and which venues keep attracting customers. Yet platforms judge these systems by their offline accuracy on past visits, a test in which the suggestions never change where people go and which therefore cannot capture long-term effects. Studying these effects in cities is challenging because, unlike online resources, travel constraints and limited venue capacity shape where people can go, while each recommended visit also changes whom other visitors encounter. To capture such features, we build a long-term simulation framework based on fine-grained human mobility data from four U.S. metropolitan areas, with distance and capacity constraints. Focusing on food venues, we study two urban consequences: how unevenly people's exposure is distributed across income groups (experienced income segregation) and the share of venues receiving no visits from simulated residents (venue disappearance). We find that, under every algorithm and in every metropolitan area, at least a fifth of venues stop receiving visits, and that more than half of this loss arises from retraining. More importantly, more accurate algorithms leave people more segregated, and the most accurate algorithm leaves people 15-21% more segregated than they actually are. We then test a re-ranking intervention that favours less popular venues and runs on top of a platform's existing algorithm. It lowers both venue disappearance and segregation across algorithms, largely without directing people to venues where they may feel less comfortable. Our results suggest that impact assessments of recommender systems should account for the feedback loop and report segregation and venue disappearance beyond accuracy.
ER -