About

My research explores computational modeling and its applications in two seemingly unrelated yet personally fascinating fields: medical sciences and quantitative trading.

In medical sciences, I am exploring how mathematical optimization can advance the diagnosis, treatment, and healthcare interventions for life-altering illness in neurology and immunology, including neuro-degenerative (e.g., Alzheimer’s disease) and neuro-developmental disorders (e.g., Autism spectrum disorder/Asperger’s), immune disorders (e.g., autoimmune diseases), and vestibular disorders (e.g., Mal de Débarquement Syndrome, MdDS).

In quantitative trading, my goal is to design computational models that empower retail and individual traders to make more informed investment decisions. This contrasts with the traditional emphasis on supporting institutional traders.

Before transitioning to academia, I worked as a data scientist in industry, leading cross-functional projects to develop large-scale, production-ready machine learning and mathematical optimization models. These models were designed to improve operational efficiency in areas such as fraud prevention, customer experience, credit risk assessment, and pricing optimization. For instance, at Capital One, I developed a novel integer-programming model to optimize fund availability for customers after check deposits while mitigating the bank’s fraud risk. Over the years, I held various roles at organizations including Goldman Sachs, Capital One, Freddie Mac, AvalonBay, and Deloitte.

Outside of work, I enjoy playing and watching sports — particularly tennis, basketball, soccer — as well as reading about history.

Publications

Refereed Journals

• Drone-Delivery Network for Opioid Overdose: Nonlinear Integer Queueing-Optimization Models and Methods, Operations Research, 2024.
  with Miguel Lejeune

• Multi‐agent search for a moving and camouflaging target, Naval Research Logistics, 2024.
  with Miguel Lejeune and Johannes Royset

• Profit-based unit commitment models with price-responsive decision-dependent uncertainty, European Journal of Operational Research, 2024.
  with Miguel Lejeune and Payman Dehghanian.

• A distributionally robust area under curve maximization model, Operations Research Letters,, 2020.
  with Miguel Lejeune

Professional Articles

• How Mathematical Optimization Helps to Improve Customer Experience and Fraud Defense for Consumer Banking, ORMS Today, 2024.

Learning

Formal Education

• Ph.D. TBD
• Ph.D. (Dropout) Operations Research, Data Sciences and Operations Department at Marshall School of Business, University of Southern California (USC)
  • Withdrew after completing one semester to return to D.C. for family reasons
• M.S. Data Science - Operations Research, George Washington University
• M.S. Statistics, Rutgers University - New Brunswick

Online Learning

Since my research is interdisciplinary and my formal education is only in the “math” part, I have relied on various resources to study “the other” part, including medical science, biology, chemistry, and physics. Below are some of the resources I have used.

• Medical Sciences

  • Introductory Human Physiology. Duke University via Coursera
  • Anatomy: Human Neuroanatomy. University of Michigan via Coursera
  • Fundamentals of Immunology Specialization. Rice University via Coursera

• Biology

  • Contemporary Biology. University of North Texas via Coursera

• Chemistry

  • Introduction to Chemistry. Duke University via Coursera

• Physics

Teaching

• Tutorial:
  • Introduction to Modeling with Gurobi Python Interface, 2022, session for PhD Students in the Decision Sciences Dept. and Smart Grid Lab at GW
    • Slides

Industry Experience

Full-Time

• Risk Strat/Quant, Goldman Sachs (Remote)
• Principal Data Scientist, Capital One (McLean, VA)
• Quantitative Analyst, Freddie Mac (McLean, VA)
• Data Scientist, AvalonBay Communities (AVB) (Arlington, VA)
• Data Analyst, Deloitte (New York, NY)

Internship

• Audit Intern, PwC (Hong Kong)
• Audit Intern, RSM U.S./McGladrey (Chicago, IL)