Introduction

Hi, I am Saad! I am a Ph.D. candidate in Computer Science at the University of Maryland, College Park, working under the supervision of Dr. Vanessa Frias-Martinez in the Urban Computing Lab. My dissertation focuses on Auditing the accuracy and fairness of COVID-19 forecasting and modeling tasks with mobility and contextual data, where I develop frameworks to evaluate prediction models and mobility datasets for potential biases and performance disparities across different social determinants. Through my research, I aim to ensure that data-driven urban computing applications serve all communities equitably while maintaining high predictive performance, ultimately contributing to more fair and effective public health and economic policy decisions.

I completed my M.S. in Computer Science from UMD (2023) and my BSc in Computer Science and Engineering from Bangladesh University of Engineering and Technology (BUET) in 2017. My research has led to several peer-reviewed publications in venues such as PLOS One, Computers Environment and Urban Systems, ACM JCSS, EPJ Data Science. I am particularly interested in developing fair and interpretable models that can drive decision-making in high-stakes settings like public health and urban applications, while ensuring equitable outcomes across different communities.

News

• [February 2025] Paper on auditing fairness of US COVID-19 Forecast Hub models accepted at PLOS One.
• [October 2024] Presented our work on Disparate recovery trajectories of small business restaurants across USA at NetMob 2024

Research Focus

My research operates at the intersection of data science, urban computing, and fairness in AI, focusing on three key areas:

Data Curation: I develop tools and frameworks for collecting human mobility data, including BALTO, a privacy-preserving toolkit (BALTOApp and BALTODash) for gathering multimodal (mobility + transit experiences) transit data. This work ensures representative and ethical data collection practices.

Forecasting: I design and implement accurate prediction models, with a particular focus on COVID-19 case forecasting and economic recovery patterns. These models integrate multiple data sources to provide reliable predictions for decision-makers.

Auditing: I develop frameworks to audit AI systems for fairness and evaluate the role of behavioral data in predictive modeling. This work includes assessing prediction models for demographic biases and understanding how mobility data impacts model performance across different communities.

This research aims to enable efficient and equitable data-driven policy and planning, with direct applications in:

• Public Health Response
• Urban Planning
• Economic Recovery