Abstract

This project aims to build framework and an interactive dashboard for zero-coding natural language query-based spatio-temporal urban data analytics, leveraging advanced prompt engineering for Large Language Models, as well as custom models. It shall incorporate available network and deep learning models for select urban datasets from NYU Open Data and beyond, enabling their application for addressing urban analytics questions formulated through natural language prompts. Completion of the project shall open up the potential of urban data analytics to broad non-technical audience, and also contribute toward the state-of-the-art generative AI for data analytics.