Generative AI: Mining Housing Data With a Higher Powered Shovel

Dylan J. Hayden
U.S. Department of Housing and Urban Development

The views expressed in this article are those of the author and do not represent the official views or policies of the Office of Policy Development and Research or the U.S. Department of Housing and Urban Development.

This article investigates the potential applications of generative artificial intelligence (AI) models, such as Chat Generative Pre-Trained Transformer (ChatGPT), in housing research by assisting with data analysis. Using the U.S. Department of Housing and Urban Development (HUD) Picture of Subsidized Households dataset, the study employs ChatGPT to generate code and analyze correlations within a housing research context. The methodology includes creating a computer program for calculating correlations and incorporating ChatGPT to analyze the output, leveraging OpenAI’s application programming interface. The article addresses concerns related to bias, inaccuracies, and improper citation and examines the benefits and limitations of using ChatGPT in housing research. This study contributes to the ongoing conversation surrounding the responsible and effective use of generative AI models in research across various disciplines.