College Honors Program

Date of Creation

5-2025

Document Type

Thesis

Department

Computer Science

First Advisor

Farhad Mohsin

Abstract

Zoning is a powerful regulatory tool that determines how municipalities use and develop land. The goal of zoning is to classify land use (e.g., residential, commercial, industrial) to maximize compatibility among neighboring parcels. Local zoning decisions, however, are made by small-sized boards, often through an opaque process, which raises concerns about bias and fairness. In the United States, zoning has historically prioritized single-family housing and thus created economic barriers that limit access to certain communities. Given the task of classifying land use and the wealth of geographical, demographic, and infrastructural data describing each parcel, the problem of bias in zoning could benefit from an algorithmic decision-making process aimed at equity. This paper explores zoning classification as a supervised learning task based on existing data in a locality (Worcester County, Massachusetts). We extensively collect publicly available data from multiple sources to predict zoning labels with machine learning models. Our results show that accurate predictions here require relatively complex models. Furthermore, we perform counterfactual analysis using socioeconomic features to explore their influence on current zoning decisions. Taken together, this exploratory study aims to assess zoning through machine learning and highlights opportunities for future work to apply computational techniques for fair zoning designation.

Download

Share

COinS