About me

I’m passionate about engineering, intelligent data modeling, and applied machine learning with a focus on social impact.

Currently, I’m pursuing a bachelor’s degree at Oberlin College, majoring in 3-2 Engineering and Computer Science, with a concentration in data science.

As a full-stack developer, I’ve created AccessEd, a platform that expands education access for refugees, and BiteBalance, which promotes sustainability with a constant focus on making technology more equitable

In research, I used applied machine learning to support data-driven decision-making in public health

Outside work, I run on iced lattes, and the calm energy of horses

Education

Bachelor's of Arts

Major: 3-2 Engineering & Computer Science

Expected Graduation: May 2027

GPA: 3.7

Campus Engagement

Girls Who Code College Loop (President)
Muslim Students Association (MSA) (Co‑Chair)
Program Board (Member)

Fellowships

STRONG (Science and Technology Research Opportunities for a New Generation) Scholar
International Project for Peace Fellowship 2025 Recipient

Relevant Coursework

Data Structures
Algorithms
Programming Abstractions
Discrete Mathematics
Multivariable Calculus
Electricity, Magnetism and Thermodynamics
Mechanics and Relativity

Projects

AccessEd

AccessEd — Expanding Educational Opportunity

AccessEd is an educational platform for refugees facing barriers to education. The platform provides guidance, curated resources, and mentorship to help learners find academic opportunities—no matter where they are.

AccessEd is a platform that helps refugees overcome barriers to education. It brings together tools for discovering scholarships, connecting with mentors and accessing guidance

Enables users to search and navigate scholarship opportunities with step‑by‑step support
Offers mentorship community built around shared experiences
Allows users to create profiles and save resources, articles, and personalized guidance

BiteBalance — Smart Sustainability Made Personal

BiteBalance transforms sustainability into a personal journey, with tailored meal suggestions based on user weight, activities, and goals—helping you eat well and reduce waste.

BiteBalance redefines personal sustainability by making everyday nutrition effortless and environmentally conscious. Leveraging precise, science-backed analyses, the platform personalizes meal portions, minimizes waste, and showcases your impact—making healthier, greener choices intuitive and rewarding.

Dynamic, personalized recommendations that adapt to your nutrition goals
Automatic tracking and analytics to measure food waste reduction
Interactive visuals and progress dashboards to keep motivation high

Research

Overview

This ongoing research focuses on developing predictive models to understand and forecast opioid overdose death rates across the United States. By analyzing large-scale public health datasets, the project aims to identify patterns, risk factors, and geographic trends to help inform resource allocation and public health policy decisions. The team leveraged publicly available datasets to develop six machine learning models, enabling more accurate predictions

Python R TensorFlow PyTorch Scikit-learn Jupyter Notebooks

Jan–May 2024

Conducted comprehensive literature review on opioid overdose death rate prediction, integrating key insights from public health studies.
Collaborated in developing an interactive R Shiny dashboard for dynamic visualization of county-level model results, supporting both internal analysis and public dissemination.
Presented research findings at the Oberlin Undergraduate Symposium.

June–August 2024

Evaluated and optimized various neural network structures to enhance model accuracy.
Transitioned workflows from TensorFlow to PyTorch, enabling more flexible training pipelines and improved computational efficiency.
Tuned hyperparameters across six deep learning models, performed comparative analyses, and iteratively refined configurations using validation metrics.

August–December 2024

Executed predictive models on county-, state-, and national-level datasets, ensuring generalizability across geographic scales.
Evaluated and visualized comparative results using multiple metrics in R to assess model accuracy, stability, and interpretability.
Integrated demographic and socioeconomic variables to improve overall prediction performance and relevance.