Community search signatures as foundation features for human-centered geospatial modeling

TL;DR

This paper introduces a novel community-level search signature feature for geospatial modeling, demonstrating its effectiveness in predicting health, demographic, and environmental variables across US counties without requiring strict temporal alignment.

Contribution

It proposes a new aggregated, anonymized search interest feature for community-level geospatial modeling, outperforming existing methods in various predictive tasks.

Findings

Achieved an average R^2 of 0.74 for health variables

Achieved an average R^2 of 0.80 for demographic and environmental variables

Outperformed satellite imagery-based models in spatial predictions

Abstract

Aggregated relative search frequencies offer a unique composite signal reflecting people's habits, concerns, interests, intents, and general information needs, which are not found in other readily available datasets. Temporal search trends have been successfully used in time series modeling across a variety of domains such as infectious diseases, unemployment rates, and retail sales. However, most existing applications require curating specialized datasets of individual keywords, queries, or query clusters, and the search data need to be temporally aligned with the outcome variable of interest. We propose a novel approach for generating an aggregated and anonymized representation of search interest as foundation features at the community level for geospatial modeling. We benchmark these features using spatial datasets across multiple domains. In zip codes with a population greater than 3000 that cover over 95% of the contiguous US population, our models for predicting missing values in a 20% set of holdout counties achieve an average $R^2$ score of 0.74 across 21 health variables, and 0.80 across 6 demographic and environmental variables. Our results demonstrate that these search features can be used for spatial predictions without strict temporal alignment, and that the resulting models outperform spatial interpolation and state of the art methods using satellite imagery features.