Subhajit Bag

Subhajit Bag

MS Analytics @ Georgia Tech | Ex-American Express | IIT KGP Grad | Machine Learning

About Me - Subhajit Bag

Hi! I’m Subhajit Bag, a graduate student at the Georgia Institute of Technology, pursuing an M.S. in Analytics (expected December 2026).
I’m passionate about Machine Learning, Interpretable AI, and Graph Representation Learning, and I aim to use these tools to uncover deeper insights from complex data.

Education

  • M.S. in Analytics, Georgia Institute of Technology (2025–2026)
    Focus: Machine Learning, Data Science, and Computational Statistics

  • B.Tech in Chemical Engineering with Minor in Mathematics, IIT Kharagpur (Graduated 2023)

Experience

  • Analyst - AI Research, American Express (Jun 2023 – Jul 2025)
    Built a LLM powered Insight Generation Engine to automate case studies.
    Focused on Data Shapley and model explainability for real-world datasets.

  • Research Intern, IIM Ahmedabad (Summer 2022)

    Advisor - Prof. Indranil Bose

    Research Area - Cybersecurity policy assessment using temporal knowledge graphs

  • Research Intern, IIM Ranchi (Summer 2022)

    Advisor - Prof. Sobhan Sarkar

    Research Area - Manifold learning, Traffic Safety Analytics.

  • Data Science Intern, Truminds Software Systems (Summer 2021)
    Built interpretable models to find reasons behind tunnel down events in servers.

Publications

  • Enhancing Cybersecurity Risk Assessment using Temporal Knowledge Graph-Based Explainable Decision Support System
    Decision Support Systems, 2025.
    Authors: Subhajit Bag, Sobhan Sarkar, Indranil Bose.

  • SENE: A Novel Manifold Learning Approach for Distracted Driving Analysis with Spatio-Temporal and Driver Praxeological Features
    Engineering Applications of Artificial Intelligence, 2023.
    Authors: Subhajit Bag, Rahul Golder, Sobhan Sarkar, Saptashwa Maity.

➡️ See the complete list on my Publications page.

Research Interests

  • Interpretable Machine Learning – Understanding how models make predictions
  • Graph Neural Networks (GNNs) – Representation learning on structured data
  • Shapley Values & Data Valuation – Quantifying the importance of training data
  • Optimization & Learning Theory – Mathematical foundations of modern ML
  • Decision Support Systems – Explainable models for high-stakes domains

Beyond Research

Outside of academics, I enjoy:

  • Playing the guitar and ukulele 🎶
  • Reading books on philosophy, science, and creativity 📚
  • Loves learning languages and exploring different cultures 🌎