Arpit Gupta, Generative Regulatory Measurement: The Case of US Housing Regulation

Arpit Gupta, Generative Regulatory Measurement: The Case of US Housing Regulation, Monday December, 2nd , 2024;
16..00 Jerusalem Time; 15.00 CET; 14.00 London; 9.00 AM Eastern Time
We present a novel method called "generative regulatory measurement'' that uses Large Language Models (LLMs) to interpret statutes and administrative documents. The paper demonstrates the effectiveness of the tool in analyzing municipal US zoning codes, achieving 96% accuracy in binary classification tasks and a 0.92 correlation in predicting minimum lot sizes. The results establish five facts about American zoning: (1) Housing production disproportionately happens in unincorporated areas without municipal zoning codes. (2) Density in the form of multifamily apartments and small lot single family homes is broadly limited. (3) Zoning follows a monocentric pattern with regional variations, with suburban regulations particularly strict in the Northeast. (4) Housing regulations can be clustered into two main principal components, the first of which corresponds to housing complexity and can be interpreted as extracting value in high demand environments. (5) The second principal component associates with exclusionary zoning.
Arpit Gupta joined New York University Stern School of Business as an Assistant Professor of Finance in September 2016. Professor Gupta's research interests focus on using large datasets to understand default dynamics in household finance, real estate and corporate finance. Recent papers examine the role for foreclosure contagion in mortgage markets and estimate the impact of adverse health events on foreclosures and bankruptcies. He is the recipient of the 2016 Top Finance Graduate Award at Copenhagen Business School. He received his B.S. in Mathematics and Economics at the University of Chicago and his Ph.D. in Finance and Economics from Columbia Business School.