arXiv subjects

Naman Awasthi

Publications and source records attributed to Naman Awasthi.

8 recordsLinked to original sources

arXiv2026

Do LLMs Know Your Neighborhood? Auditing LLM Priors for Neighborhood-Level Mobility Prediction and Structural Alignment

Human mobility is central to urban planning, transportation, public health, and emergency response, yet fine-grained trajectory data are often proprietary, restricted, and privacy-sensitive. Large language models (LLMs) offer a potential alternative by generating plausible mobility traces and predicting individual movement, but their ability to infer aggregate neighborhood-level mobility remains unclear. We evaluate zero-shot LLMs on Census Block Group-level mobility prediction across four U.S. metropolitan areas using anonymized Cuebiq data to construct point-level, trajectory-level, and temporal mobility outcomes, paired with sociodemographic and built-environment predictors. We compare LLM predictions with supervised baselines and introduce a directional alignment analysis to test whether LLM-implied predictor effects agree with empirical OLS and Jonckheere-Terpstra trends. Supervised models achieve 0.580 average accuracy, compared with 0.435 for the best LLM, with spatial extent outcomes showing the strongest predictability but also the largest LLM-baseline gaps. Directional analysis shows that LLMs often rely on coarse, stable predictor-level priors that remain similar across outcomes and cities, including asymmetric treatment of protected-group predictors. Overall, LLMs can partially recover aggregate mobility patterns from urban context, but their predictions should not be treated as structurally grounded without auditing empirical alignment and potential bias.

cs.LG↗

arXiv2025

Auditing the Fairness of the US COVID-19 Forecast Hub's Case Prediction Models

The US COVID-19 Forecast Hub, a repository of COVID-19 forecasts from over 50 independent research groups, is used by the Centers for Disease Control and Prevention (CDC) for their official COVID-19 communications. As such, the Forecast Hub is a critical centralized resource to promote transparent decision making. While the Forecast Hub has provided valuable predictions focused on accuracy, there is an opportunity to evaluate model performance across social determinants such as race and urbanization level that have been known to play a role in the COVID-19 pandemic. In this paper, we carry out a comprehensive fairness analysis of the Forecast Hub model predictions and we show statistically significant diverse predictive performance across social determinants, with minority racial and ethnic groups as well as less urbanized areas often associated with higher prediction errors. We hope this work will encourage COVID-19 modelers and the CDC to report fairness metrics together with accuracy, and to reflect on the potential harms of the models on specific social groups and contexts.

stat.AP↗

arXiv2025

From "I have nothing to hide" to "It looks like stalking": Measuring Americans' Level of Comfort with Individual Mobility Features Extracted from Location Data

Location data collection has become widespread with smart phones becoming ubiquitous. Smart phone apps often collect precise location data from users by offering \textit{free} services and then monetize it for advertising and marketing purposes. While major tech companies only sell aggregate behaviors for marketing purposes; data aggregators and data brokers offer access to individual location data. Some data brokers and aggregators have certain rules in place to preserve privacy; and the FTC has also started to vigorously regulate consumer privacy for location data. In this paper, we present an in-depth exploration of U.S. privacy perceptions with respect to specific location features derivable from data made available by location data brokers and aggregators. These results can provide policy implications that could assist organizations like the FTC in defining clear access rules. Using a factorial vignette survey, we collected responses from 1,405 participants to evaluate their level of comfort with sharing different types of location features, including individual trajectory data and visits to points of interest, available for purchase from data brokers worldwide. Our results show that trajectory-related features are associated with higher privacy concerns, that some data broker based obfuscation practices increase levels of comfort, and that race, ethnicity and education have an effect on data sharing privacy perceptions. We also model the privacy perceptions of people as a predictive task with F1 score \textbf{0.6}.

cs.CY↗

arXiv2024

DemOpts: Fairness corrections in COVID-19 case prediction models

COVID-19 forecasting models have been used to inform decision making around resource allocation and intervention decisions e.g., hospital beds or stay-at-home orders. State of the art deep learning models often use multimodal data such as mobility or socio-demographic data to enhance COVID-19 case prediction models. Nevertheless, related work has revealed under-reporting bias in COVID-19 cases as well as sampling bias in mobility data for certain minority racial and ethnic groups, which could in turn affect the fairness of the COVID-19 predictions along race labels. In this paper, we show that state of the art deep learning models output mean prediction errors that are significantly different across racial and ethnic groups; and which could, in turn, support unfair policy decisions. We also propose a novel de-biasing method, DemOpts, to increase the fairness of deep learning based forecasting models trained on potentially biased datasets. Our results show that DemOpts can achieve better error parity that other state of the art de-biasing approaches, thus effectively reducing the differences in the mean error distributions across more racial and ethnic groups.

cs.LG↗

arXiv2024

COVID-19's Unequal Toll: An assessment of small business impact disparities with respect to ethnorace in metropolitan areas in the US using mobility data

Early in the pandemic, counties and states implemented a variety of non-pharmacological interventions (NPIs) focused on mobility, such as national lockdowns or work-from-home strategies, as it became clear that restricting movement was essential to containing the epidemic. Due to these restrictions, businesses were severely affected and in particular, small, urban restaurant businesses. In addition to that, COVID-19 has also amplified many of the socioeconomic disparities and systemic racial inequities that exist in our society. The overarching objective of this study was to examine the changes in small urban restaurant visitation patterns following the COVID-19 pandemic and associated mobility restrictions, as well as to uncover potential disparities across different racial/ethnic groups in order to understand inequities in the impact and recovery. Specifically, the two key objectives were: 1) to analyze the overall changes in restaurant visitation patterns in US metropolitan areas during the pandemic compared to a pre-pandemic baseline, and 2) to investigate differences in visitation pattern changes across Census Block Groups with majority Asian, Black, Hispanic, White, and American Indian populations, identifying any disproportionate effects. Using aggregated geolocated cell phone data from SafeGraph, we document the overall changes in small urban restaurant businesses' visitation patterns with respect to racial composition at a granularity of Census Block Groups. Our results show clear indications of reduced visitation patterns after the pandemic, with slow recoveries. Via visualizations and statistical analyses, we show that reductions in visitation patterns were the highest for small urban restaurant businesses in majority Asian neighborhoods.

cs.CY↗

arXiv2024

Assessing the Impact of Case Correction Methods on the Fairness of COVID-19 Predictive Models

One of the central difficulties of addressing the COVID-19 pandemic has been accurately measuring and predicting the spread of infections. In particular, official COVID-19 case counts in the United States are under counts of actual caseloads due to the absence of universal testing policies. Researchers have proposed a variety of methods for recovering true caseloads, often through the estimation of statistical models on more reliable measures, such as death and hospitalization counts, positivity rates, and demographics. However, given the disproportionate impact of COVID-19 on marginalized racial, ethnic, and socioeconomic groups, it is important to consider potential unintended effects of case correction methods on these groups. Thus, we investigate two of these correction methods for their impact on a downstream COVID-19 case prediction task. For that purpose, we tailor an auditing approach and evaluation protocol to analyze the fairness of the COVID-19 prediction task by measuring the difference in model performance between majority-White counties and majority-minority counties. We find that one of the correction methods improves fairness, decreasing differences in performance between majority-White and majority-minority counties, while the other method increases differences, introducing bias. While these results are mixed, it is evident that correction methods have the potential to exacerbate existing biases in COVID-19 case data and in downstream prediction tasks. Researchers planning to develop or use case correction methods must be careful to consider negative effects on marginalized groups.

physics.soc-ph↗

arXiv2024

Systematic analysis of the effectiveness of adding human mobility data to covid-19 case prediction linear models

Human mobility data has been extensively used in covid-19 case prediction models. Nevertheless, related work has questioned whether mobility data really helps that much. We present a systematic analysis across mobility datasets and prediction lookaheads and reveal that adding mobility data to predictive models improves model performance only for about two months at the onset of the testing period, and that performance improvements -- measured as predicted vs. actual correlation improvement over non-mobility baselines -- are at most 0.3.

cs.CY↗

arXiv2023

Developing an Effective and Automated Patient Engagement Estimator for Telehealth: A Machine Learning Approach

We discuss MET, a learning-based algorithm proposed for perceiving a patient's level of engagement during telehealth sessions. We leverage latent vectors corresponding to Affective and Cognitive features frequently used in psychology literature to understand a person's level of engagement in a semi-supervised GAN-based framework. We showcase the efficacy of this method from the perspective of mental health and more specifically how this can be leveraged for a better understanding of patient engagement during telemental health sessions. To further the development of similar technologies that can be useful for telehealth, we also plan to release a dataset MEDICA containing 1299 video clips, each 3 seconds long and show experiments on the same. Our framework reports a 40% improvement in RMSE (Root Mean Squared Error) over state-of-the-art methods for engagement estimation. In our real-world tests, we also observed positive correlations between the working alliance inventory scores reported by psychotherapists. This indicates the potential of the proposed model to present patient engagement estimations that aligns well with the engagement measures used by psychotherapists.

cs.CV↗