Irene Aldridge, Ellie Bae, Siddhesh Darak, Nicholas Donat, Akhil Fernando-Bell, Bella Ge, Nicholas Goguen-Compagnoni, Ishita Gupta, Ali Hasan, Pierce Hoenigman, Imran Isa-Dutse, Jiwon Jeong, Tishya Khanna, Neha Konduru, Yixuan Liu, Kai Maeda, Nolan McKenna, Karl Muller, Farzaan Naeem, Rishabh Patel, Zachary Sheldon, Ammar Syed, Nathan Tai, Michael Twersky, Haoying Wang, Zening Wang, Zexun Yao, Nadav Yochman
arXiv 7 May 2026 · Econometrics
arXiv:2605.06482 · PDF · DOI · OpenAlex · Extracted main text
Municipal 311 call centers and complaint intake systems face a structural mismatch between incoming volume and classification capacity. The staff and heuristics available to triage, route, and prioritize complaints cannot scale with demand. This bottleneck produces differential service quality that follows income and racial lines (\cite{liu2024sla}). We develop an equity-centered reinforcement learning (RL) framework that augments call classification capacity across six New York City Department of Buildings (DOB) operational domains: boiler safety, crane and derrick oversight, heat and hot water complaints, housing complaint triage, scaffold safety, and Natural Area District (SNAD) protection. Rather than replacing human classifiers, our agents act as intelligent intake routers: learning to assign incoming complaints to action categories: escalate, batch, defer, inspect now. The proposed technique is designed to maximize throughput, minimize misclassification cost, and actively narrow historical equity gaps in service delivery. We formalize each domain as a Markov Decision Process (MDP) in which equitable classification coverage is a first-class reward objective. Post-hoc SHAP attribution reveals that complaint recurrence and neighborhood-level statistics are stronger predictors of actionable violations than raw complaint volume. This finding has direct implications for complaint routing given the demographic correlates of those features.
appendix boundary found by appendix_command · 95% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Zhi Liu and Uma Bhandaram and Nikhil Garg (2023) Quantifying Spatial Under-reporting Disparities in Resident Crowdsourcing | 1.000 | 17 | 8 | 100% |
| 2 | Zhi Liu and Nikhil Garg (2024) Redesigning Service Level Agreements: Equity and Efficiency in City Government Operations | 1.000 | 12 | 7 | 100% |
| 3 | Gabriel Agostini and Emma Pierson and Nikhil Garg (2024) A Bayesian Spatial Model to Correct Under-Reporting in Urban Crowdsourcing | 1.000 | 9 | 7 | 100% |
| 4 | Jeffrey A. Burke and Deborah Estrin and Mark Hansen and Andrew Parke… (2006) Participatory Sensing | 1.000 | 8 | 6 | 100% |
| 5 | Deborah Estrin (2014) Small Data, Where n = Me | 1.000 | 5 | 4 | 100% |
| 6 | Catherine D'Ignazio and Lauren F. Klein (2023) Data Feminism | 0.644 | 2 | 2 | 100% |
| 7 | Edward L. Glaeser and Andrew Hillis and Scott D. Kominers and Michae… (2016) Crowdsourcing City Government: Using Tournaments to Improve Inspection Accuracy | 0.644 | 2 | 2 | 100% |
| 8 | Volodymyr Mnih and Koray Kavukcuoglu and David Silver and Andrei A.… (2015) Human-Level Control through Deep Reinforcement Learning | 0.644 | 2 | 2 | 100% |
| 9 | Ronald J. Williams (1992) Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning | 0.644 | 2 | 2 | 100% |
| 10 | Jackson A. Killian and Bryan Wilder and Amit Sharma and Vinod Choudh… (2019) Learning to Prescribe Interventions for Tuberculosis Patients Using Digital Adherence Data | 0.511 | 2 | 1 | 100% |
Showing the top 10 of 21 scored citations.